Method, system, and computer program product for orthogonally encoding features in a learned vector representation

Abstract

Methods, systems, and computer program products for orthogonally encoding features in a learned vector representation are provided. An example method may include allocating a first plurality of coordinates of a latent vector embedding of a machine learning model, orthogonally encoding a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding, training the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels, and performing one or more classification tasks based on the augmented latent vector embedding.

Description

METHOD, SYSTEM, AND COMPUTER PROGRAM PRODUCT FOR ORTHOGONALLY ENCODING FEATURES IN A LEARNED VECTOR REPRESENTATIONCROSS REFERENCE TO RELATED APPLICATION

[0001] The present application claims the benefit of United States Provisional Patent Application No. 63 / 650,027, filed on May 21 , 2024, the disclosure of which is hereby incorporated by reference in its entirety.BACKGROUND1 . Technical Field

[0002] This disclosure relates generally to vector representations, such as embeddings, used in machine learning models and, in some non-limiting embodiments or aspects, to methods, systems, and computer program products for orthogonally encoding features in a learned vector representation.2. Technical Considerations

[0003] Machine learning is a field of computer science that may use statistical techniques to provide a computer system with the ability to learn (e.g., to progressively improve performance of) a task with data without the computer system being explicitly programmed to perform the task. In some instances, machine learning models may be developed for sets of data so that the machine learning models can perform a task (e.g., a task associated with a prediction) with regard to the set of data.

[0004] In some instances, a machine learning model, such as a predictive machine learning model, may be used to make a prediction regarding a risk or an opportunity based on data. A predictive machine learning model may be used to analyze a relationship between the performance of a unit based on data associated with the unit and one or more known features of the unit. The objective of the predictive machine learning model may be to assess the likelihood that a similar unit will exhibit the performance of the unit. A predictive machine learning model may be used as a fraud detection model. For example, predictive machine learning models may perform calculations based on data associated with payment transactions to evaluate the risk or opportunity of a payment transaction involving a customer, in order to guide a decision of whether to authorize the payment transaction.

[0005] An embedding (e.g., a neural embedding) may refer to a relatively lowdimensional space into which high-dimensional vectors can be translated. In some examples, the embedding may include a vector that has values which represent relationships of semantics of inputs by placing semantically similar inputs closer together in an embedding space. In some instances, embeddings may improve the performance of machine learning techniques on large inputs, such as sparse vectors representing words. For example, embeddings may be learned and reused across machine learning models.

[0006] In some instances, embeddings may be used to learn information from a database. However, in some instances, operations may need to be performed before embeddings may be used to learn the information from the database. For example, a pseudo-document and / or a graph may be required to be generated on top of the database before an embedding can be used to learn information from the database. Furthermore, where embedding values lack orthogonality between other embedding values of other classes, features of the class may not have as high of a projection score on a vector for a similar class as the class of the embedding as compared to dissimilar classes.SUMMARY

[0007] Accordingly, provided are improved methods, systems, and computer program products for orthogonally encoding features in a learned vector representation.

[0008] According to non-limiting embodiments or aspects, provided is a method for orthogonally encoding features in a learned vector representation. In some nonlimiting embodiments or aspects, the method may include allocating a first plurality of coordinates of a latent vector embedding of a machine learning model. In some nonlimiting embodiments or aspects, the method may further include orthogonally encoding a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding. In some non-limiting embodiments or aspects, the method may further include training the machine learning model based on a training dataset to provide a trained machine learning model that may include an augmented latent vector embedding. The training dataset may include a plurality of data points having a second plurality of labels. The first plurality of labels may be included in the secondplurality of labels. In some non-limiting embodiments or aspects, the method may further include performing one or more classification tasks based on the augmented latent vector embedding.

[0009] In some non-limiting embodiments or aspects, the machine learning model may include an autoencoder.

[0010] In some non-limiting embodiments or aspects, a second plurality of coordinates of the latent vector embedding may not allocated based on the first plurality of labels associated with the classification task.

[0011] In some non-limiting embodiments or aspects, orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding may include encoding one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0012] In some non-limiting embodiments or aspects, training the machine learning model based on the training dataset to provide the trained machine learning model may include training the machine learning model based on a plurality of loss functions. The plurality of loss functions may include at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0013] In some non-limiting embodiments or aspects, the method may further include generating a second machine learning model to include the augmented latent vector embedding. In some non-limiting embodiments or aspects, performing the one or more classification tasks may include performing the one or more classification tasks using the second machine learning model.

[0014] In some non-limiting embodiments or aspects, allocating the first plurality of coordinates of the latent vector embedding of the machine learning model may include allocating the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0015] According to non-limiting embodiments or aspects, provided is a system for orthogonally encoding features in a learned vector representation. In some nonlimiting embodiments or aspects, the system may include at least one processorconfigured to allocate a first plurality of coordinates of a latent vector embedding of a machine learning model. In some non-limiting embodiments or aspects, the at least one processor may be further configured to orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding. In some non-limiting embodiments or aspects, the at least one processor may be further configured to train the machine learning model based on a training dataset to provide a trained machine learning model that may include an augmented latent vector embedding. The training dataset may include a plurality of data points having a second plurality of labels. The first plurality of labels may be included in the second plurality of labels. In some non-limiting embodiments or aspects, the at least one processor may be further configured to perform one or more classification tasks based on the augmented latent vector embedding.

[0016] In some non-limiting embodiments or aspects, the machine learning model may include an autoencoder.

[0017] In some non-limiting embodiments or aspects, a second plurality of coordinates of the latent vector embedding may not be allocated based on the first plurality of labels associated with the classification task.

[0018] In some non-limiting embodiments or aspects, when orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, the at least one processor may be further configured to encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0019] In some non-limiting embodiments or aspects, when training the machine learning model based on the training dataset to provide the trained machine learning model, the at least one processor may be further configured to train the machine learning model based on a plurality of loss functions. The plurality of loss functions may include at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0020] In some non-limiting embodiments or aspects, the at least one processor may be further configured to generate a second machine learning model to include the augmented latent vector embedding. In some non-limiting embodiments or aspects, when performing the one or more classification tasks, the at least one processor may be further configured to perform the one or more classification tasks using the second machine learning model.

[0021] In some non-limiting embodiments or aspects, when allocating the first plurality of coordinates of the latent vector embedding of the machine learning model, the at least one processor may be further configured to allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0022] According to non-limiting embodiments or aspects, provided is a computer program product for orthogonally encoding features in a learned vector representation. In some non-limiting embodiments or aspects, the computer program product may include at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to allocate a first plurality of coordinates of a latent vector embedding of a machine learning model. In some non-limiting embodiments or aspects, the program instructions may further cause the at least one processor to orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding. In some non-limiting embodiments or aspects, the program instructions may further cause the at least one processor to train the machine learning model based on a training dataset to provide a trained machine learning model that may include an augmented latent vector embedding. The training dataset may include a plurality of data points having a second plurality of labels. The first plurality of labels may be included in the second plurality of labels. In some non-limiting embodiments or aspects, the program instructions may further cause the at least one processor to perform one or more classification tasks based on the augmented latent vector embedding.

[0023] In some non-limiting embodiments or aspects, the machine learning model may include an autoencoder.

[0024] In some non-limiting embodiments or aspects, a second plurality of coordinates of the latent vector embedding may not be allocated based on the first plurality of labels associated with the classification task.

[0025] In some non-limiting embodiments or aspects, the program instructions that cause the at least one processor to orthogonally encode the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, may further cause the at least one processor to encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0026] In some non-limiting embodiments or aspects, the program instructions that cause the at least one processor to train the machine learning model based on the training dataset to provide the trained machine learning model, may cause the at least one processor to train the machine learning model based on a plurality of loss functions. The plurality of loss functions may include at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0027] In some non-limiting embodiments or aspects, the program instructions may further cause the at least one processor to generate a second machine learning model to include the augmented latent vector embedding. In some non-limiting embodiments or aspects, the program instructions that cause the at least one processor to perform the one or more classification tasks may cause the at least one processor to perform the one or more classification tasks using the second machine learning model.

[0028] In some non-limiting embodiments or aspects, the program instructions that cause the at least one processor to allocate the first plurality of coordinates of the latent vector embedding of the machine learning model, may further cause the at least one processor to allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0029] Further non-limiting embodiments or aspects are set forth in the following numbered clauses:

[0030] Clause 1 : A computer-implemented method, comprising: allocating, with at least one processor, a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encoding, with at least one processor, a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding; training, with at least one processor, the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and performing, with at least one processor, one or more classification tasks based on the augmented latent vector embedding.

[0031] Clause 2: The computer-implemented method of clause 1 , wherein the machine learning model comprises an autoencoder.

[0032] Clause 3: The computer-implemented method of clause 1 or 2, wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.

[0033] Clause 4: The computer-implemented method of any of clauses 1 -3, wherein orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding comprises: encoding one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0034] Clause 5: The computer-implemented method of any of clauses 1 -4, wherein training the machine learning model based on the training dataset to provide the trained machine learning model comprises: training the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0035] Clause 6: The computer-implemented method of any of clauses 1 -5, further comprising: generating a second machine learning model to include the augmented latent vector embedding; wherein performing the one or more classification taskscomprises: performing the one or more classification tasks using the second machine learning model.

[0036] Clause 7: The computer-implemented method of any of clauses 1 -6, wherein allocating the first plurality of coordinates of the latent vector embedding of the machine learning model comprises: allocating the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0037] Clause 8: A system, comprising: at least one processor configured to: allocate a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding; train the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and perform one or more classification tasks based on the augmented latent vector embedding.

[0038] Clause 9: The system of clause 8, wherein the machine learning model comprises an autoencoder.

[0039] Clause 10: The system of clause 8 or 9, wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.

[0040] Clause 1 1 : The system of any of clauses 8-10, wherein, when orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, the at least one processor is configured to: encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0041] Clause 12: The system of any of clauses 8-1 1 , wherein, when training the machine learning model based on the training dataset to provide the trained machine learning model, the at least one processor is configured to: train the machine learningmodel based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0042] Clause 13: The system of any of clauses 8-12, wherein the at least one processor is further configured to: generate a second machine learning model to include the augmented latent vector embedding; and wherein, when performing the one or more classification tasks, the at least one processor is configured to: perform the one or more classification tasks using the second machine learning model.

[0043] Clause 14: The system of any of clauses 8-13, wherein, when allocating the first plurality of coordinates of the latent vector embedding of the machine learning model, the at least one processor is configured to: allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0044] Clause 15: A computer program product, including at least one non- transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to: allocate a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding; train the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and perform one or more classification tasks based on the augmented latent vector embedding.

[0045] Clause 16: The computer program product of clause 15, wherein the machine learning model comprises an autoencoder.

[0046] Clause 17: The computer program product of clause 15 or 16, wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.

[0047] Clause 18: The computer program product of any of clauses 15-17, wherein, the program instructions that cause the at least one processor to orthogonally encodethe plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, cause the at least one processor to: encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0048] Clause 19: The computer program product of any of clauses 15-18, wherein, the program instructions that cause the at least one processor to train the machine learning model based on the training dataset to provide the trained machine learning model, cause the at least one processor to: train the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0049] Clause 20: The computer program product of any of clauses 15-19, wherein the program instructions further cause the at least one processor to: generate a second machine learning model to include the augmented latent vector embedding; and wherein, the program instructions that cause the at least one processor to perform the one or more classification tasks, cause the at least one processor to: perform the one or more classification tasks using the second machine learning model.

[0050] Clause 21 : The computer program product of any of clauses 15-20, wherein, the program instructions that cause the at least one processor to allocate the first plurality of coordinates of the latent vector embedding of the machine learning model, cause the at least one processor to: allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0051] These and other features and characteristics of the present disclosure, as well as the methods of operation and functions of the related elements of structures and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate corresponding parts in the various figures. It is to be expressly understood, however, that the drawings are for the purpose ofillustration and description only and are not intended as a definition of the limits of the disclosed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Additional advantages and details are explained in greater detail below with reference to the non-limiting, exemplary embodiments that are illustrated in the accompanying schematic figures, in which:

[0053] FIG. 1 is a schematic diagram of a system for orthogonally encoding features in a learned vector representation, according to some non-limiting embodiments or aspects;

[0054] FIG. 2 is a flow diagram of a process for orthogonally encoding features in a learned vector representation, according to some non-limiting embodiments or aspects;

[0055] FIGS. 3A-3H are schematic diagrams of an exemplary implementation of a system and / or method for orthogonally encoding features in a learned vector representation, according to some non-limiting embodiments or aspects;

[0056] FIG. 4 is a diagram of an exemplary environment in which systems, methods, and / or computer program products, described herein, may be implemented, according to some non-limiting embodiments or aspects; and

[0057] FIG. 5 is a schematic diagram of example components of one or more devices of FIG. 1 and / or FIG. 4, according to some non-limiting embodiments or aspects.DETAILED DESCRIPTION

[0058] For purposes of the description hereinafter, the terms “end,” “upper,” “lower,” “right,” “left,” “vertical,” “horizontal,” “top,” “bottom,” “lateral,” “longitudinal,” and derivatives thereof shall relate to the embodiments as they are oriented in the drawing figures. However, it is to be understood that the present disclosure may assume various alternative variations and step sequences, except where expressly specified to the contrary. It is also to be understood that the specific devices and processes illustrated in the attached drawings, and described in the following specification, are simply exemplary and non-limiting embodiments or aspects of the disclosed subject matter. Hence, specific dimensions and other physical characteristics related to the embodiments or aspects disclosed herein are not to be considered as limiting.

[0059] Some non-limiting embodiments or aspects are described herein in connection with thresholds. As used herein, satisfying a threshold may refer to a value being greater than the threshold, more than the threshold, higher than the threshold, greater than or equal to the threshold, less than the threshold, fewer than the threshold, lower than the threshold, less than or equal to the threshold, equal to the threshold, etc.

[0060] No aspect, component, element, structure, act, step, function, instruction, and / or the like used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the articles “a” and “an” are intended to include one or more items and may be used interchangeably with “one or more” and “at least one.” Furthermore, as used herein, the term “set” is intended to include one or more items (e.g., related items, unrelated items, a combination of related and unrelated items, and / or the like) and may be used interchangeably with “one or more” or “at least one.” Where only one item is intended, the term “one” or similar language is used. Also, as used herein, the terms “has,” “have,” “having,” or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise. In addition, reference to an action being “based on” a condition may refer to the action being “in response to” the condition. For example, the phrases “based on” and “in response to” may, in some non-limiting embodiments or aspects, refer to a condition for automatically triggering an action (e.g., a specific operation of an electronic device, such as a computing device, a processor, and / or the like).

[0061] As used herein, the term “acquirer institution” may refer to an entity licensed and / or approved by a transaction service provider to originate transactions (e.g., payment transactions) using a payment device associated with the transaction service provider. The transactions the acquirer institution may originate may include payment transactions (e.g., purchases, original credit transactions (OCTs), account funding transactions (AFTs), and / or the like). In some non-limiting embodiments or aspects, an acquirer institution may be a financial institution, such as a bank. As used herein, the term “acquirer system” may refer to one or more computing devices operated by or on behalf of an acquirer institution, such as a server computer executing one or more software applications.

[0062] As used herein, the term “account identifier” may include one or more primary account numbers (PANs), tokens, or other identifiers associated with acustomer account. The term “token” may refer to an identifier that is used as a substitute or replacement identifier for an original account identifier, such as a PAN. Account identifiers may be alphanumeric or any combination of characters and / or symbols. Tokens may be associated with a PAN or other original account identifier in one or more data structures (e.g., one or more databases, and / or the like) such that they may be used to conduct a transaction without directly using the original account identifier. In some examples, an original account identifier, such as a PAN, may be associated with a plurality of tokens for different individuals or purposes.

[0063] As used herein, the term “communication” may refer to the reception, receipt, transmission, transfer, provision, and / or the like of data (e.g., information, signals, messages, instructions, commands, and / or the like). For one unit (e.g., a device, a system, a component of a device or system, combinations thereof, and / or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and / or transmit information to the other unit. This may refer to a direct or indirect connection (e.g., a direct communication connection, an indirect communication connection, and / or the like) that is wired and / or wireless in nature. Additionally, two units may be in communication with each other even though the information transmitted may be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit may be in communication with a second unit if at least one intermediary unit processes information received from the first unit and communicates the processed information to the second unit. In some non-limiting embodiments or aspects, a message may refer to a network packet (e.g., a data packet and / or the like) that includes data. It will be appreciated that numerous other arrangements are possible.

[0064] As used herein, the term “computing device” may refer to one or more electronic devices configured to process data. A computing device may, in some examples, include the necessary components to receive, process, and output data, such as a processor, a display, a memory, an input device, a network interface, and / or the like. A computing device may be a mobile device. As an example, a mobile device may include a cellular phone (e.g., a smartphone or standard cellular phone), a portable computer, a wearable device (e.g., watches, glasses, lenses, clothing, and / orthe like), a personal digital assistant (PDA), and / or other like devices. A computing device may also be a desktop computer or other form of non-mobile computer.

[0065] As used herein, the term “server” may refer to or include one or more computing devices that are operated by or facilitate communication and processing for multiple parties in a network environment, such as the Internet, although it will be appreciated that communication may be facilitated over one or more public or private network environments and that various other arrangements are possible. Further, multiple computing devices (e.g., servers, point-of-sale (POS) devices, mobile devices, etc.) directly or indirectly communicating in the network environment may constitute a “system.”

[0066] As used herein, the term “system” may refer to one or more computing devices or combinations of computing devices and / or components of such (e.g., processors, servers, client devices, software applications, and / or the like). Reference to “a device,” “a server,” “a processor,” and / or the like, as used herein, may refer to a previously-recited device, server, or processor that is recited as performing a previous step or function, a different device, server, or processor, and / or a combination of devices, servers, and / or processors. For example, as used in the specification and the claims, a first device, a first server, or a first processor that is recited as performing a first step or a first function may refer to the same or different device, server, or processor recited as performing a second step or a second function.

[0067] As used herein, the term “issuer institution” may refer to one or more entities, such as a bank, that provide accounts to customers for conducting transactions (e.g., payment transactions), such as initiating credit and / or debit payments. For example, an issuer institution may provide an account identifier, such as a PAN, to a customer that uniquely identifies one or more accounts associated with that customer. The account identifier may be embodied on a portable financial device, such as a physical financial instrument, e.g., a payment card, and / or may be electronic and used for electronic payments. The term “issuer system” refers to one or more computer devices operated by or on behalf of an issuer institution, such as a server computer executing one or more software applications. For example, an issuer system may include one or more authorization servers for authorizing a transaction.

[0068] As used herein, the term “merchant” may refer to an individual or entity that provides goods and / or services, or access to goods and / or services, to customers based on a transaction, such as a payment transaction. The term “merchant” or“merchant system” may also refer to one or more computer systems operated by or on behalf of a merchant, such as a server computer executing one or more software applications.

[0069] As used herein, the term “payment device” may refer to an electronic payment device, a portable financial device (e.g., a payment card, such as a credit or debit card), a gift card, a smartcard, smart media, a payroll card, a healthcare card, a wristband, a machine-readable medium containing account information, a keychain device or fob, a radio frequency identification (RFID) transponder, a retailer discount or loyalty card, a cellular phone, an electronic wallet mobile application, a PDA, a pager, a security card, a computing device, an access card, a wireless terminal, a transponder, and / or the like. In some non-limiting embodiments or aspects, the payment device may include volatile or non-volatile memory to store information (e.g., an account identifier, a name of the account holder, and / or the like).

[0070] As used herein, a “point-of-sale (POS) device” may refer to one or more devices, which may be used by a merchant to conduct a transaction (e.g., a payment transaction) and / or process a transaction. For example, a POS device may include one or more client devices. Additionally or alternatively, a POS device may include peripheral devices, card readers, scanning devices (e.g., code scanners), Bluetooth® communication receivers, near-field communication (NFC) receivers, RFID receivers, and / or other contactless transceivers or receivers, contact-based receivers, payment terminals, and / or the like. As used herein, a “point-of-sale (POS) system” may refer to one or more client devices and / or peripheral devices used by a merchant to conduct a transaction. For example, a POS system may include one or more POS devices and / or other like devices that may be used to conduct a payment transaction. In some non-limiting embodiments or aspects, a POS system (e.g., a merchant POS system) may include one or more server computers configured to process online payment transactions through webpages, mobile applications, and / or the like.

[0071] As used herein, the term “transaction service provider” may refer to an entity that receives transaction authorization requests from merchants or other entities and provides guarantees of payment, in some cases through an agreement between the transaction service provider and an issuer institution. For example, a transaction service provider may include a payment network such as Visa® or any other entity that processes transactions. The term “transaction processing system” may refer to one or more computer systems operated by or on behalf of a transaction serviceprovider, such as a transaction processing server executing one or more software applications. A transaction processing server may include one or more processors and, in some non-limiting embodiments or aspects, may be operated by or on behalf of a transaction service provider.

[0072] Non-limiting embodiments or aspects of the disclosed subject matter are directed to methods, systems, and computer program products for orthogonally encoding features in a learned vector representation. The disclosed subject matter provides for allocating a first plurality of coordinates of a latent vector embedding of a machine learning model, orthogonally encoding a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding, training the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, where the training dataset comprises a plurality of data points having a second plurality of labels and the first plurality of labels is included in the second plurality of labels, and performing one or more classification tasks based on the augmented latent vector embedding. In some non-limiting embodiments or aspects, the machine learning model comprises an autoencoder. In some non-limiting embodiments or aspects, a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task. In some non-limiting embodiments or aspects, orthogonally encoding the plurality of features corresponding to one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding includes encoding one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0073] In some non-limiting embodiments or aspects, training the machine learning model based on the training dataset to provide the trained machine learning model includes training the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0074] In some non-limiting embodiments or aspects, the disclosed subject matter further provides for generating a second machine learning model to include theaugmented latent vector embedding, and performing the one or more classification tasks includes performing the one or more classification tasks using the second machine learning model. In some non-limiting embodiments or aspects, allocating the first plurality of coordinates of the latent vector embedding of the machine learning model includes allocating the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

[0075] In this way, the disclosed subject matter may provide a machine learning model, such as an autoencoder machine learning model, that includes a latent vector embedding with a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task orthogonally encoded in a first plurality of coordinates of the latent vector embedding. With this, the disclosed subject matter may provide for a learned vector representation that avoids degrading performance associated with other embedding techniques, and that improves both reconstruction and classification accuracy of a machine learning model that performs classification tasks in association with the latent vector embedding. Accordingly, the disclosed subject matter is unique and unconventional.

[0076] For the purpose of illustration, in the following description, while the presently disclosed subject matter is described with respect to methods, systems, and computer program products for orthogonally encoding features in a learned vector representation, e.g., for analysis of characteristics of electronic payment transactions represented as a time series, one skilled in the art will recognize that the disclosed subject matter is not limited to the non-limiting embodiments or aspects disclosed herein. For example, the methods, systems, and computer program products described herein may be used with a wide variety of settings, such as a machine learning model that is used for making determinations (e.g., predictions, classifications, regressions, and / or the like) with at least one machine learning model based on a dataset, such as for fraud detection / prevention, authorization, authentication, identification, feature selection, product recommendation, and / or the like.

[0077] Referring now to FIG. 1 , shown is example system 100 for orthogonally encoding features in a learned vector representation, according to some non-limiting embodiments or aspects. For example, system 100 may include model managementsystem 102, machine learning (ML) model management database 104, user device 106, and / or communication network 108.

[0078] Model management system 102 may include one or more devices capable of receiving information from and / or communicating information to ML model management database 104 and / or user device 106 (e.g., directly via wired or wireless communication connection, indirectly via communication network 108, and / or the like). For example, model management system 102 may include a computing device, such as a server, a group of servers, a desktop computer, a portable computer, a mobile device, and / or other like devices. In some non-limiting embodiments or aspects, model management system 102 may be in communication with a data storage device (e.g., ML model management database 104), which may be local or remote to model management system 102. In some non-limiting embodiments or aspects, model management system 102 may be capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage device (e.g., ML model management database 104).

[0079] ML model management database 104 may include one or more devices capable of receiving information from and / or communicating information to model management system 102 and / or user device 106 (e.g., directly via wired or wireless communication connection, indirectly via communication network 108, and / or the like). For example, ML model management database 104 may include a computing device, such as a server, a group of servers, a desktop computer, a portable computer, a mobile device, and / or other like devices. In some non-limiting embodiments or aspects, ML model management database 104 may include a data storage device. In some non-limiting embodiments or aspects, ML model management database 104 may be capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage device. In some non-limiting embodiments or aspects, ML model management database 104 may be part of model management system 102 and / or part of the same system as model management system 102.

[0080] User device 106 may include one or more devices capable of receiving information from and / or communicating information to model management system 102 and / or ML model management database 104 (e.g., directly via wired or wireless communication connection, indirectly via communication network 108, and / or the like). For example, user device 106 may include a computing device, such as a mobiledevice, a portable computer, a desktop computer, and / or other like devices. Additionally or alternatively, each user device 106 may include a device capable of receiving information from and / or communicating information to other user devices 106 (e.g., directly via wired or wireless communication connection, indirectly via communication network 108, and / or the like). In some non-limiting embodiments or aspects, user device 106 may be part of model management system 102 and / or part of the same system as model management system 102. For example, model management system 102, ML model management database 104, and user device 106 may all be (and / or be part of) a single system and / or a single computing device.

[0081] Communication network 108 may include one or more wired and / or wireless networks. For example, communication network 108 may include a cellular network (e.g., a long-term evolution (LTE®) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, and / or the like), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the public switched telephone network (PSTN)), a private network (e.g., a private network associated with a transaction service provider), an ad hoc network, an intranet, the Internet, a fiber optic-based network, a cloud computing network, and / or the like, and / or a combination of these or other types of networks.

[0082] The number and arrangement of systems and devices shown in FIG. 1 are provided as an example. There may be additional systems and / or devices, fewer systems and / or devices, different systems and / or devices, and / or differently arranged systems and / or devices than those shown in FIG. 1. Furthermore, two or more systems or devices shown in FIG. 1 may be implemented within a single system or device, or a single system or device shown in FIG. 1 may be implemented as multiple, distributed systems or devices. Additionally or alternatively, a set of systems (e.g., one or more systems) or a set of devices (e.g., one or more devices) of system 100 may perform one or more functions described as being performed by another set of systems or another set of devices of system 100.

[0083] Referring now to FIG. 2, shown is a flow diagram for process 200 for orthogonally encoding features in a learned vector representation, according to some non-limiting embodiments or aspects. The steps shown in FIG. 2 are for example purposes only. It will be appreciated that additional, fewer, different, and / or different order of steps may be used in non-limiting embodiments or aspects. In some non-limiting embodiments or aspects, a step may be automatically performed in response to performance and / or completion of a prior step. In some non-limiting embodiments or aspects, process 200 may be performed during a training process. In some nonlimiting embodiments or aspects, one or more of the steps of process 200 may be performed (e.g., completely, partially, and / or the like) by model management system 102 (e.g., at least one computing device of model management system 102). In some non-limiting embodiments or aspects, one or more of the steps of process 200 may be performed (e.g., completely, partially, and / or the like) by another system, another device, another group of systems, or another group of devices, separate from or including model management system 102, such as ML model database 104, user device 106, and / or the like.

[0084] As shown in FIG. 2, at step 202, process 200 may include allocating a first plurality of coordinates of a latent vector embedding of a machine learning model. For example, model management system 102 may allocate (e.g., designate, assign, reserve, etc.) a first plurality of coordinates of a latent vector embedding of a machine learning model. In some non-limiting embodiments or aspects, the machine learning model may include an autoencoder machine learning model.

[0085] In some non-limiting embodiments or aspects, model management system 102 may allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of a first plurality of labels associated with a classification task for an input to be provided to the machine learning model. For example, model management system 102 may allocate a number of coordinates of the latent vector embedding based on a number of labels in the first plurality of labels associated with the classification task for the input. In some non-limiting embodiments or aspects, the number of coordinates of the latent vector embedding may correspond to the number of labels in the first plurality of labels associated with the classification task for the input. In some non-limiting embodiments or aspects, the number of coordinates of the latent vector embedding may correspond to a number of predictions to be made that are associated with the classification task for the input.

[0086] In some non-limiting embodiments or aspects, a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task. In some non-limiting embodiments or aspects, the machine learning model may include an autoencoder. In some nonlimiting embodiments or aspects, the second plurality of coordinates of the latentvector embedding may include a larger number of coordinates than the first plurality of coordinates of the latent vector embedding.

[0087] As shown in FIG. 2, at step 204, process 200 may include encoding a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task. For example, model management system 102 may encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task.

[0088] In some non-limiting embodiments or aspects, model management system 102 may encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task. In some examples, the plurality of features may include a large number of features, such as 100 features, 500 features, 1 ,000 features, 5,000 features, 10,000 features, 25,000 features, 50,000 features, 100,000 features, 1 ,000,000 features, and / or the like.

[0089] In some non-limiting embodiments or aspects, the plurality of features may represent the plurality of transaction parameters. In some non-limiting embodiments or aspects, the plurality of transaction parameters may include electronic wallet card data associated with an electronic card (e.g., an electronic credit card, an electronic debit card, an electronic loyalty card, and / or the like), decision data associated with a decision (e.g., a decision to approve or deny a transaction authorization request), authorization data associated with an authorization response (e.g., an approved spending limit, an approved transaction value, and / or the like), a PAN, an authorization code (e.g., a personal identification number (PIN), etc.), data associated with a transaction amount (e.g., an approved limit, a transaction value, etc.), data associated with a transaction date and time, data associated with a conversion rate of a currency, data associated with a merchant type (e.g., a merchant category code that indicates a type of goods, such as grocery, fuel, and / or the like), data associated with an acquiring institution country, data associated with an identifier of a country associated with the PAN, data associated with a response code, data associated with a merchant identifier (e.g., a merchant name, a merchant location, and / or the like), data associated with a type of currency corresponding to funds stored in association with the PAN, and / or the like.

[0090] As shown in FIG. 2, at step 206, process 200 may include training the machine learning model based on a training dataset. For example, model management system 102 may train the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding. In some non-limiting embodiments or aspects, the training dataset includes a plurality of data points having a second plurality of labels and the first plurality of labels may be included in the second plurality of labels.

[0091] In some examples, the training dataset may include a large amount of data points (e.g., data instances), such as 100 data points, 500 data points, 1 ,000 data points, 5,000 data points, 10,000 data points, 25,000 data points, 50,000 data points, 100,000 data points, 1 ,000,000 data points, and / or the like.

[0092] In some non-limiting embodiments or aspects, each data point may include transaction data associated with the transaction. In some non-limiting embodiments or aspects, the transaction data may include a plurality of transaction parameters associated with an electronic payment transaction. In some non-limiting embodiments or aspects, each data point may include one or more features of a plurality of features, which may represent the plurality of transaction parameters. In some non-limiting embodiments or aspects, the plurality of transaction parameters may include electronic wallet card data associated with an electronic card (e.g., an electronic credit card, an electronic debit card, an electronic loyalty card, and / or the like), decision data associated with a decision (e.g., a decision to approve or deny a transaction authorization request), authorization data associated with an authorization response (e.g., an approved spending limit, an approved transaction value, and / or the like), a PAN, an authorization code (e.g., a personal identification number (PIN), etc.), data associated with a transaction amount (e.g., an approved limit, a transaction value, etc.), data associated with a transaction date and time, data associated with a conversion rate of a currency, data associated with a merchant type (e.g., a merchant category code that indicates a type of goods, such as grocery, fuel, and / or the like), data associated with an acquiring institution country, data associated with an identifier of a country associated with the PAN, data associated with a response code, data associated with a merchant identifier (e.g., a merchant name, a merchant location, and / or the like), data associated with a type of currency corresponding to funds stored in association with the PAN, and / or the like.

[0093] In some non-limiting embodiments or aspects, model management system 102 may train the machine learning model based on a plurality of loss functions. In some non-limiting embodiments or aspects, the plurality of loss functions may include at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

[0094] As shown in FIG. 2, at step 208, process 200 may include performing one or more classification tasks. For example, model management system 102 may perform one or more classification tasks based on an augmented latent vector embedding. In some non-limiting embodiments or aspects, model management system 102 may generate a second machine learning model to include the augmented latent vector embedding, and model management system 102 may perform the one or more classification tasks using the second machine learning model.

[0095] In some non-limiting embodiments or aspects, model management system 102 may determine whether to perform an action (e.g., an action associated with authorization of an electronic payment transaction, an action associated with determining whether an electronic payment transaction is fraudulent, etc.) based on an inference of the second machine learning model. For example, model management system 102 may determine to perform an action based on the inference of the second machine learning model (e.g., the second machine learning model to include the augmented latent vector embedding) being equal to a first value. In such an example, model management system 102 may determine to forgo performing an action based on the inference of the second machine learning model being equal to a second value (e.g., a second value that is different from the first value).

[0096] In some non-limiting embodiments or aspects, model management system 102 may receive a request for inference for a machine learning model (e.g., the second machine learning model that has been placed into a production or runtime environment), and model management system 102 may generate an inference based on the request. In some non-limiting embodiments or aspects, the second machine learning model may include a machine learning model that has been trained and / or validated (e.g., tested) and that may be used to generate inferences (e.g., predictions), such as real-time inferences, runtime inferences, and / or the like. In some non-limiting embodiments or aspects, a production machine learning model may include the updated and / or trained second machine learning model.

[0097] In some non-limiting embodiments or aspects, the request for inference may be associated with a task for which the second machine learning model may provide an inference. In some non-limiting embodiments or aspects, the request for inference may be associated with financial service tasks. For example, the request for inference may be associated with a token service task, an authentication task (e.g., a 3D secure authentication task), a fraud detection task, and / or the like.

[0098] In some non-limiting embodiments or aspects, the request for inference may include runtime input data. In some non-limiting embodiments or aspects, the runtime input data may include a sample of data that is received by the machine learning model in real-time with respect to the runtime input data being generated. For example, runtime input data may be generated by a data source (e.g., a customer performing a transaction) and may be subsequently received by the second machine learning model in real-time. Runtime (e.g., production) may refer to inputting runtime data (e.g., a runtime dataset, real-world data, real-world observations, and / or the like) into one or more second machine learning models (e.g., one or more trained second machine learning models of model management system 102) and / or generating an inference (e.g., generating an inference using model management system 102 or another system).

[0099] In some non-limiting embodiments or aspects, runtime may be performed during a phase which may occur after a training phase, after a testing phase, and / or after deployment of the second machine learning model into a production environment. During a time period associated with the runtime phase, the machine learning model (e.g., a production machine learning model) may process the runtime input data to generate inferences (e.g., real-time inferences, real-time predictions, and / or the like).

[0100] Referring now to FIGS. 3A-3H, shown are schematic diagrams of implementation 300 of a process (e.g., process 200) for orthogonally encoding features in a learned vector representation, according to come non-limiting embodiments or aspects. In some non-limiting embodiments or aspects, one or more of the steps of the process may be performed (e.g., completely, partially, etc.) by model management system 102 (e.g., one or more devices of model management system 102). In some non-limiting embodiments or aspects, one or more of the steps of the process may be performed (e.g., completely, partially, etc.) by another device or a group of devices separate from or including model management system 102 (e.g., one or more devices of model management system 102), ML model managementdatabase 104, and / or user device 106. In some non-limiting embodiments or aspects, latent vector embedding 320 may include a plurality of coordinates. The plurality of coordinates may include a first plurality of coordinates and / or a second plurality of coordinates.

[0101] As shown by reference number 302 in FIG. 3A, model management system 102 may generate a latent vector embedding of a machine learning model. For example, model management system 102 may allocate a first plurality of coordinates of latent vector embedding 320 of machine learning model 314. In some non-limiting embodiments or aspects, model management system 102 may include one or more machine learning models. For example, model management system 102 may generate (e.g., train, re-train, update, and / or maintain) one or more machine learning models. In some non-limiting embodiments or aspects, the one or more machine learning models may include machine learning model 314. In some non-limiting embodiments or aspects, machine learning model 314 may be trained to perform a task (e.g., a classification task) based on receiving an input (e.g., an input image). In some non-limiting embodiments or aspects, machine learning model 314 may include an autoencoder. In some non-limiting embodiments or aspects, machine learning model 314 may include a plurality of layers. For example, machine learning model 314 may include encoding layer 316 and / or embedding layer 318.

[0102] In some non-limiting embodiments or aspects, encoding layer 316 may include an encoder and / or a decoder (e.g., one or more encoder machine learning models and / or one or more decoder machine learning models). In some non-limiting embodiments or aspects, encoding layer 316 may include an autoencoder (e.g., a variational autoencoder). The autoencoder may include a latent layer. In some nonlimiting embodiments or aspects, a classification task may be encoded directly into the latent layer. In some non-limiting embodiments or aspects, encoding layer 316 may include a deep learning model (e.g., a transformer model), a convolutional neural network model (e.g., a U-net model used for image segmentation tasks), and / or a generative model (e.g., a diffusion model). In some non-limiting embodiments or aspects, model management system 102 may train encoding layer 316 to perform a reconstruction task (e.g., reconstructing an image) based on receiving an input (e.g., an image). In some non-limiting embodiments or aspects, the encoding layer may generate and / or provide an output based on receiving the input.

[0103] In some non-limiting embodiments or aspects, the input may include an input vector. The input vector may be generated based on an image. For example, the input vector may include a 12288-dimensional input vector generated based on a 64x64 image with three color channels. In some non-limiting embodiments or aspects, encoding layer 316 may include embedding layer 318. Embedding layer 318 may include a low-dimensional latent layer between an encoder and a decoder. Embedding layer 318 may include latent vector embedding 320. In some non-limiting embodiments or aspects, latent vector embedding 320 may be a latent representation (e.g., representing the embedded vector) of the input vector. Latent vector embedding 320 may include latent dimensions (e.g., dimensions such as {80, 120, 160, 200, 240}). In some non-limiting embodiments or aspects, latent vector embedding 320 may include structured dimensions and / or unstructured dimensions. The structured dimensions may include multi-label predictions. In some non-limiting embodiments or aspects, model management system 102 may move a k-label prediction to be inside latent vector embedding 320.

[0104] As shown by reference number 304 in FIG. 3B, model management system 102 may allocate a first plurality of coordinates of the latent vector embedding. For example, model management system 102 may allocate the first plurality of coordinates (e.g., the first k coordinates) of latent vector embedding 320 by reserving the first k coordinates of embedding layer 318 to correspond to predictions for the k labels, wherein k is a number of labels (e.g., k=40). In some non-limiting embodiments or aspects, an input to embedding layer 318 may be labeled as true (e.g., +1 ) or false (e.g., -1 ). In some non-limiting embodiments or aspects, a dimension of embedding layer 318 may be larger than k (e.g., greater than 40).

[0105] In some non-limiting embodiments or aspects, model management system 102 may allocate the first plurality of coordinates of latent vector embedding 320 based on each label of a first plurality of labels associated with a classification task for an input to be provided to machine learning model 314. In some non-limiting embodiments or aspects, model management system 102 may not allocate the second plurality of coordinates of latent vector embedding 320 based on the first plurality of labels associated with the classification task.

[0106] As shown by reference number 306 in FIG. 3C, model management system 102 may orthogonally encode a plurality of features. For example, model management system 102 may orthogonally encode (e.g., via encoding layer 316) a plurality offeatures corresponding to one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of latent vector embedding 312. In some non-limiting embodiments or aspects, the plurality of features may include features associated with an individual in an image, such as, bald, blurry, double chin, eyeglasses, male, female, mouth open, mustache, narrow eyes, no beard, pale skin, smiling, straight hair, wearing a necklace, wearing a necktie, young, etc.

[0107] In some non-limiting embodiments or aspects, model management system 102 may encode (e.g., via encoding layer 316) one or more of the first plurality of coordinates of latent vector embedding 320 to have a binary value (e.g., 0 or 1 ) based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

[0108] As shown by reference number 308 in FIG. 3D, model management system 102 may receive a training dataset. For example, machine learning model 314 may receive a training dataset as an input from ML model management database 104. In some non-limiting embodiments or aspects, the training dataset may include a plurality of data points having a second plurality of labels. In some non-limiting embodiments or aspects, the first plurality of labels may be included in the second plurality of labels.

[0109] In some non-limiting embodiments or aspects, the training dataset may include a plurality of distinct identities, a plurality of face images, a plurality of binary attribute annotations associated with the plurality of face images, a plurality of landmark locations, and / or any combination thereof. For example, the training dataset may include a large-scale face attributes dataset with 10,177 distinct identities, 202,599 face images, 40 binary attributes annotations per image, and 5 landmark locations. In some non-limiting embodiments or aspects, model management system 102 may center crop and scale the plurality of face images to 64 x 64 pixels. In some non-limiting embodiments or aspects, the training dataset may include a well-defined multi-label classification task in the k = 40 attributes.

[0110] In some non-limiting embodiments or aspects, model management system 102 may train machine learning model 314 based on the training dataset. For example, model management system 102 may train machine learning model 314 to perform a task (e.g., a classification task) based on inputting the training dataset into machine learning model 314. In some non-limiting embodiments or aspects, modelmanagement system 102 may train machine learning model 314 for a plurality of epochs (e.g., 30 epochs) and a batch size of 64.

[0111] As shown by reference number 310 in FIG. 3E, model management system 102 may train the machine learning model. For example, model management system 102 may train machine learning model 314 based on the training dataset and / or one or more functions (e.g., a plurality of loss functions).

[0112] As shown in FIG. 3F, the plurality of loss functions may include a label matching loss function. In some non-limiting embodiments or aspects, the label matching loss function may be based on the following equation, where u = (iti, ..., uk~) e {-1, +l}kis a ground truth label, and where v = (vlt...,vk) is a predicted label:

[0113] In some non-limiting embodiments or aspects, model management system 102 may apply the label matching loss function to the structured dimensions of latent vector embedding 320, where for each image, an averageerror in the prediction of the structured dimensions may be reported.

[0114] The plurality of loss functions may include a decoder loss function. In some non-limiting embodiments or aspects, the decoder loss Ldmay be a mean squared error (MSE) loss between the input image x and the output image A(x) considering y4(-) = £>(£■(■)) as an autoencoder. In some non-limiting embodiments or aspects, the decoder loss function may be based on the following equation, where || ■ denotes the normalized squared L2norm, i.e. for z = (z1;...,zd) e

[0115] The plurality of loss functions may include a content loss function. In some non-limiting embodiments or aspects, the content loss function may be based on the following equation:

[0116] In some non-limiting embodiments or aspects, model management system 102 may leverage the first three feature extraction layers of a model as a loss network.For example, model management system 102 may pass both the input image and the reconstructed image to a network model, extract the features from 3 chosen layers for both input image and the reconstructed image, and penalize the MSE loss between the two sets of vectors and calculate the average. In some non-limiting embodiments or aspects, htmay be the ReLU-activated neurons of ithconvolution layers of the network model and x may be the input image. For auto-encoder A let xhA x)i denote the input to the layer htin the network model when x and A(x) are passed to the network model, respectively. Then the content loss of x and A(x) may be the content loss function.

[0117] In some non-limiting embodiments or aspects, the content loss function may preserve features of the input image, preventing the reconstructed image (e.g., the auto-encoded image) from being blurry in comparison to the input image.

[0118] The plurality of loss functions may include a decorrelation encouraging loss function. In some non-limiting embodiments or aspects, the decorrelation encouraging loss function may be based on the following equation:

[0119] In some non-limiting embodiments or aspects, model management system 102 may remove information associated with labels from being represented in the unstructured portion of latent vector embedding 320. Model management system 102 may generate representations of each label in the structured portion of latent vector embedding 320, as a mean of embedded images, and force each mean to be close to an origin, for example, using a batch of training data denoted by B. In some nonlimiting embodiments or aspects, a set of batch points in the jth class may be Bj = {x e B \yj = +1}. In some non-limiting embodiments or aspects, Eu(x) is the representation of training point x embedded in the unstructured part of latent vector embedding 320, j e [1. . k] is a trait, \Bt| is a size of Bt, lBjis the characteristic function of Bj (e.g., 1 if Bj is nonempty and 0 otherwise). In some non-limiting embodiments or aspects, a class within a batch may be empty, therefore the lBjmay be necessary to prevent dividing by zero.

[0120] In some non-limiting embodiments or aspects, when applying the decorrelation encouraging loss function, the unstructured dimensions of latent vector embedding 320 may be used by the decoder (e.g., to capture non-generic aspects of the background of an input image or individuals in an input image, which may not be encoded as any of the k traits).

[0121] In some non-limiting embodiments or aspects, without the decorrelation loss, the auto-encoder may freely encode features in the unstructured portion of latent vector embedding 320 in addition to the information in the structured dimensions. For example, Table 4 (below) shows the average of across all j e[l..fc] where Xj is the training data with the jth feature. As the distance in the embedding between having a label (+1 ) and not (-1 ) is 2, this scale represents 8% and 11 % of the information associated with a feature. Thus, while the label information is not entirely removed from the unstructured portion of latent vector embedding 320, the disclosed method is effective by ignoring the unstructured portion. In some non-limiting embodiments or aspects, a larger batch size and / or additional model training, may remove this effect.Table 4: Average norm of unstructured dimensions on training data Latent unst ctured dimension 40 80 120 .160 200Average norm of Eu) 0.1643 0.1908 0.0418 0.2045 0.2179

[0122] In some non-limiting embodiments or aspects, the plurality of loss functions may include a total loss function including a weighted sum of the label matching loss, the decoder loss, the content loss, and the decorrelation encouraging loss, based on the following equation:

[0123] As shown by reference number 31 1 in FIG. 3G, model management system 102 may provide a trained machine learning model. For example, model management system 102 may provide trained machine learning model 322 based on training machine learning model 314. Trained machine learning model 322 may include augmented latent vector embedding 324.

[0124] Augmented latent vector embedding 324 may include an updated feature of the plurality of features corresponding to the one or more labels of the first plurality of labels. For example, when generating augmented latent vector embedding 324, model management system 102 may update a first feature of the plurality of features corresponding to the one or more labels of the first plurality of labels to provide the updated feature. In some non-limiting embodiments or aspects, the first feature may be updated to ensure that an input image maintains a recognizable feature (e.g., glasses or a mustache), or to reduce associates with a gender bias.

[0125] In some non-limiting embodiments or aspects, when generating augmented latent vector embedding 324, model management system 102 may identify how the first feature is represented in latent vector embedding 320 and / or update (e.g., minimally) the vectorized representation to satisfy the criteria of the first feature. In some non-limiting embodiments or aspects, the feature may be identified with a linear classifier which may be determined by a distance along a single normal direction. Model management system 102 may update the feature along a single direction in a high-dimensional space by identifying the direction and determining an amount to shift the representation in the direction.

[0126] In some non-limiting embodiments or aspects, for a class j e [1. . k] model management system 102 may build representative vectors z for positive and z7“ for negative instances. Model management system 102 may use z (and likewise for z,") as the average embedded representation F(x) of all training data points with +1 for that label, where the representative direction is ~z}= z -

[0127] In some non-limiting embodiments or aspects, model management system 102 may update (e.g., minimally) an encoded representation z = F(x) using the representative direction z^ for class j. Model management system 102 may add this vector to z ■— > z' = z + z7. Model management system 102 may decode z' as D(z') to obtain the augmented data (e.g., the input image with an added mustache).

[0128] In some non-limiting embodiments or aspects, model management system 102 may not identify how the first feature is represented in latent vector embedding 320, for example, for a structured portion of latent vector embedding 320 where the representation of the / th feature has already been encoded in the / th coordinate. In some non-limiting embodiments or aspects, model management system 102 may manipulate a representation to have feature / by setting the / th coordinate to +1 .

[0129] In some non-limiting embodiments or aspects, model management system 102 may generate (e.g., train, re-train, update, and / or maintain) a second machine learning model (not shown). For example, model management system 102 may generate the second machine learning model to include augmented latent vector embedding 324.

[0130] As shown by reference number 312 in FIG. 3H, model management system 102 may perform one or more classification tasks. For example, machine learning model 314 may perform one or more classification tasks using trained machine learning model 322 based on augmented latent vector embedding 324.

[0131] In some non-limiting embodiments or aspects, model management system 102 may perform the one or more classification tasks using the second machine learning model.

[0132] Referring now to FIG. 4, depicted is a diagram of example payment processing network 400, according to non-limiting embodiments or aspects. In some non-limiting embodiments or aspects, payment processing network 400 may be used in conjunction with the methods, systems, and / or computer program products described herein, and / or the methods, systems, and / or computer program products described herein may be implemented in payment processing network 400. As shown in FIG. 4, payment processing network 400 may include transaction processing system 402, payment gateway system 412, merchant system 408, issuer system 404, acquirer system 410, and / or customer device 406. In some non-limiting embodiments or aspects, each of model management system 102, ML model management database 104, and / or user device 106 of FIG. 1 may be implemented by (e.g., part of) transaction processing system 402. In some non-limiting embodiments or aspects, at least one of model management system 102, ML model management database 104, and / or user device 106 of FIG. 1 may be implemented by (e.g., part of) another system, another device, another group of systems, or another group of devices, separate from or including transaction processing system 402, such as merchant system 408, issuer system 404, acquirer system 410, customer device 406, and / or the like. For example, model management system 102 may be implemented by (e.g., part of) at least one of payment gateway system 412, merchant system 408, issuer system 404, acquirer system 410, and / or customer device 406. The systems and / or devices of FIG. 4 may communicate via communication network 414, which may include one or more wired and / or wireless communication networks.

[0133] Transaction processing system 402 may include one or more devices capable of receiving information from and / or communicating information to payment gateway system 412, merchant system 408, issuer system 404, acquirer system 410, customer device 406, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, transaction processing system 402 may be in communication with one or more issuer systems (e.g., issuer system 404), one or more acquirer systems (e.g., acquirer system 410), and / or one or more payment gateway systems (e.g., payment gateway system 412). Although only a single issuer system 404, a single acquirer system 410, and a single payment gateway system 412 are shown, it will be appreciated that transaction processing system 402 may be in communication with a plurality of issuer systems, a plurality of acquirer systems, and / or a plurality of payment gateway systems. In some non-limiting embodiments or aspects, transaction processing system 402 may include a computing device, such as a server (e.g., a transaction processing server), a group of servers, and / or other like devices. In some non-limiting embodiments or aspects, transaction processing system 402 may be in communication with a data storage device, which may be local or remote to transaction processing system 402. In some non-limiting embodiments or aspects, transaction processing system 402 may be capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage device. In some non-limiting embodiments or aspects, transaction processing system 402 may be associated with a transaction service provider, as described herein. In some non-limiting embodiments or aspects, transaction processing system 402 may also operate as an issuer system, such that both transaction processing system 402 and issuer system 404 are a single system and / or are controlled by a single entity.

[0134] Payment gateway system 412 may include one or more devices capable of receiving information from and / or communicating information to transaction processing system 402, merchant system 408, issuer system 404, acquirer system 410, customer device 406, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, payment gateway system 412 may be in communication with one or more merchant systems (e.g., merchant system 408), one or more acquirer systems (e.g., acquirer system 410), and / or one or more transaction processing systems (e.g.,transaction processing system 402). Although only a single merchant system 408, a single acquirer system 410, and a single transaction processing system 402 are shown, it will be appreciated that payment gateway system 412 may be in communication with a plurality of merchant systems, a plurality of acquirer systems, and / or a plurality of transaction processing systems. In some non-limiting embodiments or aspects, payment gateway system 412 may include a computing device, such as a server, a group of servers, and / or other like devices. In some nonlimiting embodiments or aspects, payment gateway system 412 may be associated with a payment gateway, as described herein.

[0135] Merchant system 408 may include one or more devices capable of receiving information from and / or communicating information to transaction processing system 402, payment gateway system 412, issuer system 404, acquirer system 410, customer device 406, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, merchant system 408 may be in communication with one or more payment gateway systems (e.g., payment gateway system 412), one or more acquirer systems (e.g., acquirer system 410), and / or one or more consumer devices (e.g., customer device 406). Although only a single payment gateway system 412, a single acquirer system 410, and a single customer device 406 are shown, it will be appreciated that merchant system 408 may be in communication with a plurality of payment gateway systems, a plurality of acquirer systems, and / or a plurality of consumer devices. In some non-limiting embodiments or aspects, merchant system 408 may include a computing device, such as a server, a group of servers, a client device, a group of client devices, a POS device, a POS system, computers, computer systems, peripheral devices, and / or other like devices. In some non-limiting embodiments or aspects, merchant system 408 may be associated with a merchant, as described herein. In some non-limiting embodiments or aspects, merchant system 408 may include a device capable of receiving information from and / or communicating information to customer device 406 via a short range communication connection (e.g., an NFC communication connection, an RFID communication connection, a Bluetooth® communication connection, a Zigbee® communication connection, and / or the like) with customer device 406 and / or the like. In some non-limiting embodiments or aspects, merchant system 408 may include one or more client devices. For example, merchant system 408 may include a client device that allows a merchant tocommunicate information to transaction processing system 402 (e.g., via at least one of acquirer system 410 and / or payment gateway system 412). In some non-limiting embodiments or aspects, merchant system 408 (e.g., a client device thereof, a POS device thereof, and / or the like) may also operate as a payment gateway system, such that both merchant system 408 and payment gateway system 412 are a single system and / or controlled by a single entity.

[0136] Issuer system 404 may include one or more devices capable of receiving information and / or communicating information to transaction processing system 402, payment gateway system 412, merchant system 408, acquirer system 410, customer device 406, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, issuer system 404 may be in communication with one or more transaction processing systems (e.g., transaction processing system 402) and / or one or more consumer devices (e.g., customer device 406). Although only a single transaction processing system 402 and a single customer device 406 are shown, it will be appreciated that issuer system 404 may be in communication with a plurality of transaction processing systems and / or a plurality of customer devices 406. In some non-limiting embodiments or aspects, issuer system 404 may include a computing device, such as a server, a group of servers, and / or other like devices. In some non-limiting embodiments or aspects, issuer system 404 may be associated with an issuer institution, as described herein. For example, issuer system 404 may be associated with an issuer institution that issued a credit account, debit account, credit card, debit card, a payment device, and / or the like to a user associated with customer device 406.

[0137] Acquirer system 410 may include one or more devices capable of receiving information from and / or communicating information to transaction processing system 402, payment gateway system 412, merchant system 408, issuer system 404, customer device 406, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, acquirer system 410 may be in communication with one or more transaction processing systems (e.g., transaction processing system 402), one or more payment gateway systems (e.g., payment gateway system 412), and / or one or more merchant systems (e.g., merchant system 408). Although only a single transaction processing system 402, a single payment gateway system 412, and a single merchant system 408 are shown, it will be appreciated that acquirer system 410 may be incommunication with a plurality of transaction processing systems, a plurality of payment gateway systems, and / or a plurality of merchant systems. In some nonlimiting embodiments or aspects, acquirer system 410 may include a computing device, such as a server, a group of servers, and / or other like devices. In some nonlimiting embodiments or aspects, acquirer system 410 may be associated with an acquirer institution, as described herein.

[0138] Customer device 406 may include one or more devices capable of receiving information from and / or communicating information to transaction processing system 402, payment gateway system 412, merchant system 408, issuer system 404, acquirer system 410, and / or the like (e.g., directly, indirectly, via a public and / or private communication network connection, and / or the like). For example, as shown in FIG. 4, customer device 406 may be in communication with one or more merchant systems (e.g., merchant system 408) and / or one or more issuer systems (e.g., issuer system 404). Although only a single merchant system 408 and a single issuer system 404 are shown, it will be appreciated that customer device 406 may be in communication with a plurality of merchant systems and / or a plurality of issuer systems. In some non-limiting embodiments or aspects, customer device 406 may be associated with a user to whom a credit account, debit account, credit card, debit card, a payment device, and / or the like has been issued. In some non-limiting embodiments or aspects, customer device 406 may include a computing device, such as a computer, a portable computer, a laptop computer, a tablet computer, a mobile device, a cellular phone, a smartphone, a wearable device (e.g., watches, glasses, lenses, clothing, and / or the like), a PDA, a client device, and / or other like devices. In some non-limiting embodiments or aspects, customer device 406 may include a payment device, as described herein. In some non-limiting embodiments or aspects, customer device 406 may include a device capable of receiving information from and / or communicating information to other customer devices 406 (e.g., directly, indirectly, via a public and / or private communication network connection, a short range communication connection, and / or the like). In some non-limiting embodiments or aspects, customer device 406 may include a device capable of receiving information from and / or communicating information to merchant system 408 via a short range communication connection (e.g., an NFC communication connection, an RFID communication connection, a Bluetooth® communication connection, a Zigbee® communication connection, and / orthe like) with merchant system 408 and / or the like. In some non-limiting embodiments or aspects, customer device 406 may include a client device.

[0139] In some non-limiting embodiments or aspects, transaction processing system 402 may communicate with merchant system 408 directly (e.g., via a public and / or private communication network connection and / or the like). Additionally or alternatively, transaction processing system 402 may communicate with merchant system 408 through payment gateway system 412 and / or acquirer system 410. In some non-limiting embodiments or aspects, acquirer system 410 associated with merchant system 408 may operate as payment gateway system 412 to facilitate the communication of transaction messages (e.g., authorization requests) from merchant system 408 to transaction processing system 402. In some non-limiting embodiments or aspects, merchant system 408 may communicate with payment gateway system 412 directly (e.g., via a public and / or private communication network connection and / or the like). For example, merchant system 408, that includes a physical POS device, may communicate with payment gateway system 412 through a public or private network to conduct card-present transactions. As another example, merchant system 408 that includes a server (e.g., a web server) may communicate with payment gateway system 412 through a public or private network, such as the Internet, to conduct card-not-present transactions.

[0140] For the purpose of illustration, processing a transaction (e.g., a payment transaction) may include generating a transaction message (e.g., authorization request and / or the like) based on an account identifier of a customer (e.g., accountholder associated with customer device 406 and / or the like) and / or transaction data associated with the transaction. For example, merchant system 408 (e.g., a client device of merchant system 408, a POS device of merchant system 408, and / or the like) may initiate the transaction, e.g., by generating an authorization request (e.g., in response to receiving the account identifier from a payment device and / or a portable financial device of the customer and / or the like). Merchant system 408 may communicate the authorization request to payment gateway system 412 and / or acquirer system 410. In some non-limiting embodiments or aspects, payment gateway system 412 may communicate the authorization request to acquirer system 410 and / or transaction processing system 402. Additionally or alternatively, acquirer system 410 (and / or payment gateway system 412) may communicate the authorization request to transaction processing system 402. After receiving the authorization request frommerchant system 408 that identifies the account identifier of the customer (e.g., the accountholder associated with customer device 406 and / or the account identifier), transaction processing system 402 may communicate the authorization request to issuer system 404 (e.g., the issuer system that issued the payment device and / or account identifier). Issuer system 404 may determine an authorization decision (e.g., approve, deny, and / or the like) based on the authorization request, and / or issuer system 404 may generate an authorization response based on the authorization decision and / or the authorization request. Issuer system 404 may communicate the authorization response to transaction processing system 402. Transaction processing system 402 may communicate the authorization response to acquirer system 410 and / or payment gateway system 412. In some non-limiting embodiments or aspects, acquirer system 410 may communicate the authorization response to payment gateway system 412 and / or merchant system 408. Additionally or alternatively, payment gateway system 412 (and / or acquirer system 410) may communicate the authorization response to merchant system 408.

[0141] In some non-limiting embodiments or aspects, transaction processing system 402 and / or issuer system 404 may include at least one machine learning model (e.g., at least one of a fraud detection model, a risk detection model, a transaction authorization model, a credit approval model, a product recommendation model, a classifier model, an anomaly detection model, an authentication model, any combination thereof, and / or the like). For example, the machine learning model(s) may be trained based on synthetic data generated, as described herein. Transaction processing system 402 and / or issuer system 404 may perform at least one task (e.g., generate a prediction and / or generate an embedding) based on the authorization request and the machine learning model(s). For example, performing the task(s) may include generating at least one prediction associated with fraud detection, risk detection, transaction authorization, credit approval, product recommendation, classification, anomaly detection, authentication, any combination thereof, and / or the like. In some non-limiting embodiments or aspects, transaction processing system 402 may communicate at least one message based on performing the task (e.g., generating the prediction and / or generating an embedding) to issuer system 404 (e.g., along with the authorization request). In some non-limiting embodiments or aspects, issuer system 404 may determine the authorization decision (e.g., approve, deny,and / or the like) based on the authorization request and the performance of the task (e.g., generation of the prediction and / or generation of the embedding).

[0142] For the purpose of illustration, clearing and / or settlement of a transaction may include generating a message (e.g., clearing message and / or the like) based on an account identifier of a customer (e.g., associated with customer device 406 and / or the like) and / or transaction data associated with the transaction. For example, merchant system 408 may generate at least one clearing message (e.g., a plurality of clearing messages, a batch of clearing messages, and / or the like). Merchant system 408 may communicate the clearing message(s) to acquirer system 410 (and / or payment gateway system 412, which may communicate the clearing message(s) to acquirer system 410). Acquirer system 410 may communicate the clearing message(s) to transaction processing system 402. Transaction processing system 402 may communicate the clearing message(s) to issuer system 404. Issuer system 404 may generate at least one settlement message based on the clearing message(s). In some non-limiting embodiments or aspects, issuer system 404 may communicate the settlement message(s) and / or funds to transaction processing system 402 (and / or a settlement bank system associated with transaction processing system 402), and transaction processing system 402 (and / or the settlement bank system) may communicate the settlement message(s) and / or funds to acquirer system 410. Additionally or alternatively, issuer system 404 may communicate the settlement message(s) and / or funds to acquirer system 410. In some non-limiting embodiments or aspects, acquirer system 410 may communicate the settlement message(s) and / or funds to merchant system 408 (and / or an account associated with merchant system 408).

[0143] Communication network 414 may include one or more wired and / or wireless networks. For example, communication network 414 may include a cellular network (e.g., a long-term evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, and / or the like), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the public switched telephone network (PSTN)), a private network (e.g., a private network associated with a transaction service provider), an ad hoc network, an intranet, the Internet, a fiber optic-basednetwork, a cloud computing network, and / or the like, and / or a combination of these or other types of networks.

[0144] The number and arrangement of systems, devices, and / or networks shown in FIG. 4 are provided as an example. There may be additional systems, devices, and / or networks; fewer systems, devices, and / or networks; different systems, devices, and / or networks; and / or differently arranged systems, devices, and / or networks than those shown in FIG. 4. Furthermore, two or more systems or devices shown in FIG. 4 may be implemented within a single system or device, or a single system or device shown in FIG. 4 may be implemented as multiple, distributed systems or devices. Additionally or alternatively, a set of systems (e.g., one or more systems) or a set of devices (e.g., one or more devices) of environment 400 may perform one or more functions described as being performed by another set of systems or another set of devices of environment 400.

[0145] Referring now to FIG. 5, shown is a diagram of example components of device 500, according to non-limiting embodiments or aspects. Device 500 may correspond to at least one of model management system 102, ML model management database 104, and / or user device 106 in FIG. 1 and / or at least one of transaction processing system 402, issuer system 404, customer device 406, merchant system 408, and / or acquirer system 410 in FIG. 4, as an example. In some non-limiting embodiments or aspects, such systems or devices in FIG. 1 or FIG. 4 may include at least one device 500 and / or at least one component of device 500. The number and arrangement of components shown in FIG. 5 are provided as an example. In some non-limiting embodiments or aspects, device 500 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 5. Additionally or alternatively, a set of components (e.g., one or more components) of device 500 may perform one or more functions described as being performed by another set of components of device 500.

[0146] As shown in FIG. 5, device 500 may include bus 502, processor 504, memory 506, storage component 508, input component 510, output component 512, and communication interface 514. Bus 502 may include a component that permits communication among the components of device 500. In some non-limiting embodiments or aspects, processor 504 may be implemented in hardware, firmware, or a combination of hardware and software. For example, processor 504 may include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU),an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component (e.g., a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc.) that can be programmed to perform a function. Memory 506 may include random access memory (RAM), read only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, optical memory, etc.) that stores information and / or instructions for use by processor 504.

[0147] With continued reference to FIG. 5, storage component 508 may store information and / or software related to the operation and use of device 500. For example, storage component 508 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, a solid-state disk, etc.) and / or another type of computer-readable medium. Input component 510 may include a component that permits device 500 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, etc.). Additionally or alternatively, input component 510 may include a sensor for sensing information (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.). Output component 512 may include a component that provides output information from device 500 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.). Communication interface 514 may include a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, etc.) that enables device 500 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 514 may permit device 500 to receive information from another device and / or provide information to another device. For example, communication interface 514 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a cellular network interface, and / or the like.

[0148] Device 500 may perform one or more processes described herein. Device 500 may perform these processes based on processor 504 executing software instructions stored by a computer-readable medium, such as memory 506 and / or storage component 508. A computer-readable medium may include any non-transitory memory device. A memory device includes memory space located inside of a single physical storage device or memory space spread across multiple physical storagedevices. Software instructions may be read into memory 506 and / or storage component 508 from another computer-readable medium or from another device via communication interface 514. When executed, software instructions stored in memory 506 and / or storage component 508 may cause processor 504 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software. The term “configured to,” as used herein, may refer to an arrangement of software, device(s), and / or hardware for performing and / or enabling one or more functions (e.g., actions, processes, steps of a process, and / or the like). For example, “a processor configured to” may refer to a processor that executes software instructions (e.g., program code) that cause the processor to perform one or more functions.

[0149] Although embodiments have been described in detail for the purpose of illustration, it is to be understood that such detail is solely for that purpose and that the disclosure is not limited to the disclosed embodiments or aspects, but, on the contrary, is intended to cover modifications and equivalent arrangements that are within the spirit and scope of the appended claims. For example, it is to be understood that the present disclosure contemplates that, to the extent possible, one or more features of any embodiment or aspect can be combined with one or more features of any other embodiment or aspect. In fact, any of these features can be combined in ways not specifically recited in the claims and / or disclosed in the specification. Although each dependent claim listed below may directly depend on only one claim, the disclosure of possible implementations includes each dependent claim in combination with every other claim in the claim set.

Claims

WHAT IS CLAIMED IS:1 . A computer-implemented method, comprising: allocating, with at least one processor, a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encoding, with at least one processor, a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding; training, with at least one processor, the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and performing, with at least one processor, one or more classification tasks based on the augmented latent vector embedding.

2. The computer-implemented method of claim 1 , wherein the machine learning model comprises an autoencoder.

3. The computer-implemented method of claim 1 , wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.

4. The computer-implemented method of claim 1 , wherein orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding comprises: encoding one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

5. The computer-implemented method of claim 1 , wherein training the machine learning model based on the training dataset to provide the trained machine learning model comprises: training the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

6. The computer-implemented method of claim 1 , further comprising: generating a second machine learning model to include the augmented latent vector embedding; wherein performing the one or more classification tasks comprises: performing the one or more classification tasks using the second machine learning model.

7. The computer-implemented method of claim 1 , wherein allocating the first plurality of coordinates of the latent vector embedding of the machine learning model comprises: allocating the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

8. A system, comprising: at least one processor configured to: allocate a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding;train the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and perform one or more classification tasks based on the augmented latent vector embedding.

9. The system of claim 8, wherein the machine learning model comprises an autoencoder.

10. The system of claim 8, wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.1 1 . The system of claim 8, wherein, when orthogonally encoding the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, the at least one processor is configured to: encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

12. The system of claim 8, wherein, when training the machine learning model based on the training dataset to provide the trained machine learning model, the at least one processor is configured to: train the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

13. The system of claim 8, wherein the at least one processor is further configured to: generate a second machine learning model to include the augmented latent vector embedding; and wherein, when performing the one or more classification tasks, the at least one processor is configured to: perform the one or more classification tasks using the second machine learning model.

14. The system of claim 8, wherein, when allocating the first plurality of coordinates of the latent vector embedding of the machine learning model, the at least one processor is configured to: allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

15. A computer program product, including at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to: allocate a first plurality of coordinates of a latent vector embedding of a machine learning model; orthogonally encode a plurality of features corresponding to one or more labels of a first plurality of labels associated with a classification task in the first plurality of coordinates of the latent vector embedding; train the machine learning model based on a training dataset to provide a trained machine learning model that comprises an augmented latent vector embedding, wherein the training dataset comprises a plurality of data points having a second plurality of labels, and wherein the first plurality of labels is included in the second plurality of labels; and perform one or more classification tasks based on the augmented latent vector embedding.

16. The computer program product of claim 15, wherein the machine learning model comprises an autoencoder.

17. The computer program product of claim 15, wherein a second plurality of coordinates of the latent vector embedding are not allocated based on the first plurality of labels associated with the classification task.

18. The computer program product of claim 15, wherein, the program instructions that cause the at least one processor to orthogonally encode the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task in the first plurality of coordinates of the latent vector embedding, cause the at least one processor to: encode one or more of the first plurality of coordinates of the latent vector embedding to have a binary value based on one or more features of the plurality of features corresponding to the one or more labels of the first plurality of labels associated with the classification task.

19. The computer program product of claim 15, wherein, the program instructions that cause the at least one processor to train the machine learning model based on the training dataset to provide the trained machine learning model, cause the at least one processor to: train the machine learning model based on a plurality of loss functions, wherein the plurality of loss functions comprises at least one of the following: a label matching loss function, a decoder loss function, a content loss function, a decorrelation encouraging loss function, or any combination thereof.

20. The computer program product of claim 15, wherein the program instructions further cause the at least one processor to: generate a second machine learning model to include the augmented latent vector embedding; andwherein, the program instructions that cause the at least one processor to perform the one or more classification tasks, cause the at least one processor to: perform the one or more classification tasks using the second machine learning model.21 . The computer program product of claim 15, wherein, the program instructions that cause the at least one processor to allocate the first plurality of coordinates of the latent vector embedding of the machine learning model, cause the at least one processor to: allocate the first plurality of coordinates of the latent vector embedding of a machine learning model based on each label of the first plurality of labels associated with the classification task for an input to be provided to the machine learning model.

Images