A method and device for predicting author collaboration links in citation networks based on multi-layer predictive sampling

Abstract

This application discloses a method and device for predicting author collaboration links in a citation network based on multi-layer predictive sampling. The method comprises: obtaining known data from the original citation network; constructing a citation network author relationship tensor and a latent feature matrix of multi-layer citation network author links based on the known data; constructing a target loss function for citation network author relationship prediction based on the citation network author relationship tensor, and using the target loss function to train and iteratively optimize the latent feature matrix of each layer of citation network author links; and obtaining prediction results for citation network author relationship links based on the trained latent feature matrix of each layer of citation network author links. The present invention specifically operates on tensor author relationship data and can predict author relationship links with high accuracy and in accordance with statistical laws. It can be widely used in information retrieval, network analysis and other fields.

Description

Technical Field

[0001] The present invention relates to the fields of information retrieval and network analysis, and in particular to a method and device for predicting author collaboration links in a citation network based on multi-layer prediction sampling. Background Art

[0002] With the rapid development of various networks, citation network embedding has gradually become a research hotspot. Its goal is to learn node representations while preserving the network's structure and semantic information. Citation networks contain multiple types of nodes and diverse relationships between them, which are widely present in the real world. As an important component of citation networks, author nodes have multiple connections, such as two authors co-authoring a paper or their papers containing the same keywords. Using citation network embedding representations, we can predict collaborative links between authors. Therefore, how to effectively utilize the various node relationships in citation networks to predict author collaborative links has become a key issue that urgently needs to be addressed.

[0003] Currently, many researchers typically solve the link prediction problem by extracting features and training models to calculate the weighted probabilities of links. However, these methods often rely on the selection of meta-paths, which relies heavily on domain knowledge. In addition, training neural network models typically requires a large amount of computing resources and data. When dealing with large-scale networks, limitations in computing power and data acquisition become significant bottlenecks. Real-world citation network data is often very sparse, which affects model performance and prediction accuracy. Therefore, how to effectively predict author collaboration links in citation networks and improve the accuracy and reliability of predictions has become a key issue for researchers. Summary of the Invention

[0004] Based on this, the technical problem to be solved by the present invention is to provide a method and device for predicting author collaboration links in a citation network based on multi-layer predictive sampling.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting author collaboration links in a citation network based on multi-layer predictive sampling, comprising the following steps:

[0006] S1: Obtain known data of the original citation network;

[0007] S2: Based on the known data of the original citation network, construct the citation network author relationship tensor and the latent feature matrix of the multi-layer citation network author links;

[0008] S3: Based on the citation network author relationship tensor, construct a target loss function for citation network author relationship prediction, use the target loss function to train the latent feature matrix of each layer of citation network author links, and iteratively optimize the target loss function;

[0009] S4: Based on the latent feature matrix of the author links in each layer of the citation network after training, the prediction results of the author relationship links in the citation network are obtained.

[0010] Preferably, the known data of the citation network is stored in the form of a quadruple, and the quadruple is represented as W=(a1, a2, rel, l);

[0011] Among them, a1 and a2 represent different authors in the citation network, rel represents the meta-path relationship between author a1 and author a2, and l represents the relationship link value of the author collaboration between author a1 and author a2 through the meta-path relationship rel.

[0012] Preferably, step S2 includes:

[0013] S21: Divide all the quadruple W=(a1, a2, rel, l) in the known data of the citation network into K time period data according to the meta-path relationship rel;

[0014] S22: Quadruple W based on rel=1 (1) =(a1,a2,1,l) to get W (1) Data (a1, a2, l), and according to W (1) Construct a slice matrix T with element path relation rel=1 (1) ;

[0015] S23: Select the quadruple W from the quadruple W = (a1, a2, rel, l) in sequence based on the above steps according to the remaining meta-path relations rel (2) 、W (3) ,…,W (K) , respectively construct the slice matrix T (2) 、T (3) ,…,T (K) ;

[0016] S24: Arrange the K slice matrices in ascending order according to the order of the divided meta-path relationships to construct a citation network author relationship tensor Y;

[0017] S25: Based on the known data of the citation network, construct the latent feature matrices G, D, and Q of the author links of the multi-layer citation network;

[0018] Among them, the slice matrix T (1) The size of the slice matrix T is I rows and J columns, where I and J are the number of authors, K is a positive integer, and (1) The element T in (1) ijIndicates the relationship link value between the i-th author and the j-th author under the first relationship, 1≤i≤I, 1≤j≤J, Y∈R I×J×K , R represents a set of real numbers; among them, the size of the latent feature matrix G is I rows and R columns, the size of the latent feature matrix D is J rows and R columns, and the size of the latent feature matrix Q is K rows and R columns.

[0019] Preferably, step S3 includes:

[0020] S31: Initialize the process parameters involved in the prediction of author relationship links in the citation network;

[0021] S32: Based on the citation network author relationship tensor Y and the latent feature matrices G, D, and Q of the multi-layer citation network author links, a target loss function for citation network author relationship link prediction is constructed;

[0022] S33: using the target loss function to train the latent feature matrix of the author links in each layer of the citation network and iteratively optimize the target loss function;

[0023] S34: Determine whether the target loss function satisfies the iteration termination condition. If so, terminate the iteration and output the target loss function as the target loss function after iterative optimization; if not, continue the iteration.

[0024] Preferably, the process parameters include: citation network author relationship tensor Y, latent feature matrices G, D, Q; rank R that determines the dimension of the latent feature space of the latent feature matrices G, D, Q; the number of multi-layer sampling layers N; the maximum number of training iterations max Round; the iteration number control variable round during the training process; and the convergence termination threshold τ.

[0025] Preferably, step S32 includes:

[0026] S321: Traverse the multi-layer sampling layer number n∈{1,…,N}, and use the objective function to train and obtain the latent feature matrix G of the author connection of each layer of the citation network constructed by the author relationship tensor Y and the process parameters. n ,D n ,Q n ;

[0027] S322: Iteratively optimize the objective function using the Euclidean distance as the optimization target.

[0028] Preferably, step S22 specifically uses the SGD algorithm to calculate the latent feature matrix G of the nth layer. n ,D n ,Q n Training iterations, including:

[0029] (1) Fixed D nand Q n , train G through formula (1) n :

[0030]

[0031] (2) Fixed G n and Q n , train D by formula (2) n :

[0032]

[0033] (3) Fixed G n and D n , train Q by formula (3) n :

[0034]

[0035] Among them, ← is the assignment operation, G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer, Represents the hidden feature matrix G of the nth layer respectively n ,D n ,Q n The corresponding single element, η is the learning rate, n is the number of sampling layers; y ijk represents the relationship link value of the collaboration between the i-th author and the j-th author on the k-th meta-path relationship in the citation network author relationship tensor Y; represents the final predicted value of the citation network generated data;

[0036] Where ε is the target loss function, which is expressed by the following formula (4):

[0037]

[0038] Among them, the target loss function ε is the instantaneous loss of a single element in the case of known data and generated data in the citation network at the nth layer by the following formula:

[0039]

[0040] Among them, α and β represent weights, For unknown author g i In the corresponding meta-path relation q k Next link author d j The relationship link prediction value is expressed by the following formula:

[0041]

[0042] Preferably, the iteration termination condition of step S34 is that the iteration round control variable round reaches the maximum training iteration round max Round or the difference between the prediction result of the citation network in the previous round and the prediction result of the citation network after the current round is less than the convergence termination threshold τ.

[0043] Preferably, the step S4 includes:

[0044] The K slice matrices formed by dividing the citation network author relationship tensor Y are sequentially traversed in each row, and a blank position is randomly selected from the known data of the two citation networks to predict the unknown author relationship and obtain the relationship connection prediction value. The relationship link prediction value is then mapped through a nonlinear activation function to obtain the final prediction value;

[0045] Continuously select new unknown author relationships by slice and row order and repeat the above steps until the preset conditions are met. All the final prediction values and their unknown author relationships are used to generate citation network data.

[0046] Among them, the relationship connection prediction value is mapped by a nonlinear activation function as follows:

[0047]

[0048] in, is the final predicted value; the preset condition is that the amount of data generated by the citation network is the same as the amount of data known in the citation network.

[0049] In a second aspect, an embodiment of the present application provides a citation network author collaboration link prediction device based on multi-layer prediction sampling, comprising:

[0050] A citation network known data acquisition module is used to obtain the original citation network known data;

[0051] The citation network author relationship tensor construction module is used to construct the citation network author relationship tensor and the latent feature matrix of multi-layer citation network author links based on the known data of the original citation network;

[0052] a citation network training module, configured to construct a target loss function for citation network author relationship prediction based on the citation network author relationship tensor, train the latent feature matrix of each layer of citation network author links using the target loss function, and iteratively optimize the target loss function;

[0053] The citation network author relationship link prediction module is used to obtain the prediction results of the citation network author relationship links based on the latent feature matrix of each layer of the citation network author links after training.

[0054] Compared with existing technologies, this invention offers the following advantages: It utilizes known citation network data to construct a citation network author relationship tensor and a latent feature matrix for multi-layer citation network author links. Based on this citation network author relationship tensor, it constructs a target loss function. This target loss function is then used to train and iteratively optimize the latent feature matrix for multi-layer citation network author links, generating citation network generated data. This method uses both known and unknown data to jointly optimize the prediction results for citation network author relationship links. This invention specifically operates on tensor author relationship data, enabling statistically accurate and highly accurate author relationship link prediction. It has broad application in information retrieval, network analysis, and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] A more complete understanding of the exemplary embodiments of the present invention can be obtained by referring to the following drawings. The drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings, the same reference numerals generally represent the same components or steps.

[0056] Figure 1 A flowchart of a method for predicting author collaboration links in a citation network based on multi-layer predictive sampling according to an exemplary embodiment of the present application is provided;

[0057] Figure 2 A schematic diagram of the structure of a citation network author collaboration link prediction device based on multi-layer prediction sampling according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0059] It should be noted that, unless otherwise specified, the technical or scientific terms used in this application should have the common meanings understood by those skilled in the art to which this application belongs.

[0060] In addition, the terms "first" and "second" are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0061] Example 1

[0062] The present invention provides a method for predicting author collaboration links in a citation network based on multi-layer prediction sampling, including the following steps:

[0063] S1: Obtain known data of the original citation network;

[0064] Specifically, data collection may be performed upon receiving an instruction, and the server may send instructions to the citation network by sending instructions to the original citation network known data periodically, or based on notification from the device, or based on notification from a server.

[0065] Specifically, the known data of the citation network is stored as a quadruple, represented as W = (a1, a2, rel, l); where a1 and a2 represent different authors in the citation network, rel represents the meta-path relationship between authors a1 and a2, and l represents the link value of the author collaboration between authors a1 and a2 via the meta-path relationship rel. In this embodiment, the number of multi-layer sampling layers N = 20 is pre-initialized. Then, based on the original known data of the citation network, a citation network author relationship tensor and a latent feature matrix of the multi-layer citation network author links are constructed.

[0066] Specifically, step S2 includes:

[0067] S21: Divide all the quadruple W = (a1, a2, rel, l) in the known data of the citation network into K time period data according to the meta-path relationship rel;

[0068] S22: Quadruple W based on rel=1 (1) =(a1,a2,1,l) to get W (1) Data (a1, a2, l), and according to W (1) Construct a slice matrix T with element path relation rel=1 (1) ;

[0069] S23: Select the quadruple W from the quadruple W = (a1, a2, rel, l) in sequence based on the above steps according to the remaining meta-path relations rel (2)、W (3) ,…,W (K) , respectively construct the slice matrix T (2) 、T (3) ,…,T (K) ;

[0070] S24: Arrange the K slice matrices in ascending order according to the order of the divided meta-path relationships to construct the citation network author relationship tensor Y;

[0071] S25: Based on the known data of the citation network, construct the latent feature matrix G, D, Q of the author links of the multi-layer citation network;

[0072] Among them, the slice matrix T (1) The size of the slice matrix T is I rows and J columns, where I and J are the number of authors, K is a positive integer, and (1) The element T in (1) ij Indicates the relationship link value between the i-th author and the j-th author under the first relationship, 1≤i≤I, 1≤j≤J, Y∈R I×J×K , R represents a set of real numbers; among them, the size of the latent feature matrix G is I rows and R columns, the size of the latent feature matrix D is J rows and R columns, and the size of the latent feature matrix Q is K rows and R columns.

[0073] S3: Based on the citation network author relationship tensor, a target loss function for citation network author relationship prediction is constructed. The target loss function is used to train the latent feature matrix of each layer of citation network author links and iteratively optimize the target loss function.

[0074] Specifically, step S3 includes:

[0075] S31: Initialize the process parameters involved in the prediction of author relationship links in the citation network;

[0076] S32: Based on the citation network author relationship tensor Y and the latent feature matrices G, D, and Q of the multi-layer citation network author links, a target loss function for citation network author relationship link prediction is constructed;

[0077] S33: Use the target loss function to train the latent feature matrix of the author links in each layer of the citation network and iteratively optimize the target loss function;

[0078] S34: Determine whether the target loss function meets the iteration termination condition. If so, terminate the iteration and output the target loss function as the target loss function after iterative optimization; if not, continue the iteration.

[0079] In this embodiment, the process parameters include: the citation network author relationship tensor Y, latent feature matrices G, D, and Q, where G is a latent feature matrix with I rows and R columns, D is a latent feature matrix with J rows and R columns, and Q is a latent feature matrix with K rows and R columns; the rank R that determines the dimension of the latent feature space of the latent feature matrices G, D, and Q; the number of layers N; the maximum number of training iterations max Round; the variable round that controls the number of iterations during training; and the convergence termination threshold τ.

[0080] In this embodiment, the specific operations for initializing each parameter are as follows:

[0081] (1) The rank R determines the dimension of the latent feature space of the latent feature matrices G, D, and Q and is initialized to a positive integer;

[0082] (2) The sizes of the latent feature matrices G, D, and Q are determined by the values of each dimension and the rank R of the corresponding citation network author relationship tensor Y. That is, G is a latent feature matrix with I rows and R columns, D is a latent feature matrix with J rows and R columns, and Q is a latent feature matrix with K rows and R columns. The three latent feature matrices are initialized with small random positive numbers.

[0083] (3) The maximum number of training iterations, max Round, is a variable that controls the upper limit of the iteration process and is initialized to a large positive integer. The iteration round control variable, round, is initialized to 0.

[0084] (4) The convergence termination threshold τ is a parameter used to determine whether the iterative process has converged and is initialized with 1e-5.

[0085] Specifically, step S32 includes:

[0086] S321: Traverse the multi-layer sampling layer n∈{1,…,N}, and use the objective function to train and obtain the latent feature matrix G of the author connection of each layer of the citation network constructed by the author relationship tensor Y and process parameters. n ,D n ,Q n ;

[0087] Based on the known data set Ψ and the generated data set Ω, the citation network tensor Y is constructed, and the target loss function ε is constructed, which is expressed by the following formula:

[0088]

[0089] Among them, n represents the number of layers; G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer respectively; Represents the single element value corresponding to the latent feature matrix of the nth layer; α and β represent weights; yijk represents the known entities in the author relationship tensor Y of the citation network, i.e., the collaborative relationship link value between the i-th author and the j-th author on the k-th relationship; It represents the predicted value corresponding to the generated data selected layer by layer and the final predicted value obtained through the nonlinear activation function (the citation network generated data unit of the citation network author relationship link prediction module will describe the selection strategy of the generated data in detail, and the citation network author relationship link prediction value calculation unit will also introduce the nonlinear activation function in detail).

[0090] S322: Iteratively optimize the objective function using the Euclidean distance as the optimization target.

[0091] Specifically, the target loss function uses the Euclidean distance as the optimization target. The first part of the above formula refers to the loss function on the known dataset, and the second part refers to the loss function on the generated dataset. Then, considering the two cases of the nth layer respectively, the instantaneous loss of a single element is expressed by the following formula:

[0092]

[0093] Among them, α and β represent weights, For unknown author g i In the corresponding relationship q k Next link author d j The author relationship link prediction value is expressed by the following formula:

[0094]

[0095] Specifically, the target loss function ε is iteratively optimized to minimize the value of the target loss function ε. Based on the known data set Ψ of the citation network and the data set Ω generated by the citation network, the SGD algorithm is used to optimize the latent feature matrix G of the nth layer. n ,D n ,Q n The formula for training iterations is as follows:

[0096] (1) Fixed D n and Q n , train G through formula (1) n :

[0097]

[0098] (2) Fixed G n and Q n , train D by formula (2) n :

[0099]

[0100] (3) Fixed G n and D n , train Q by formula (3) n :

[0101]

[0102] Among them, ← is the assignment operation, G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer, Represents the hidden feature matrix G of the nth layer respectively n ,D n ,Q n The corresponding single element, η is the learning rate, n is the number of sampling layers; y ijk represents the relationship link value of the collaboration between the i-th author and the j-th author on the k-th meta-path relationship in the citation network author relationship tensor Y; represents the final predicted value of the citation network generated data.

[0103] In this embodiment, the ε training iteration process reaches termination conditions in two situations. The first is that the value of the training iteration control variable round is incremented by 1 after each iteration. When the value of round reaches the maximum number of training iterations, max Round, training is terminated. The second is that during training, when the difference between the prediction evaluation index value after the end of the current iteration and the prediction evaluation index value calculated after the end of the current iteration is less than the convergence termination threshold τ = 1e-5, training is terminated.

[0104] S4: Based on the latent feature matrix of the author links in each layer of the citation network after training, the prediction results of the author relationship links in the citation network are obtained.

[0105] Specifically, step S4 includes:

[0106] The K slice matrices formed by dividing the citation network author relationship tensor Y are sequentially traversed in each row, a blank position is randomly selected from the known data of the two citation networks, and a prediction value is obtained by predicting the unknown author relationship, and the predicted value is mapped through a nonlinear activation function to obtain the final prediction value;

[0107] Continuously select new unknown author relationships by slice and row order and repeat the above steps until the preset conditions are met. All the final prediction values and their unknown author relationships are used to generate citation network data.

[0108] Among them, the relationship connection prediction value is mapped by a nonlinear activation function as follows:

[0109]

[0110] in, is the final predicted value; the preset condition is that the amount of data generated by the citation network is the same as the amount of data known in the citation network.

[0111] Specifically, we determine whether the number of generated data meets the preset condition (consistent with the number of known data). If not, we select the next generated data and make a prediction. Then, we map it through the activation function to obtain the final predicted value. Each generated data is added to the known data and stored together as a quadruple. (Note that the first layer only has known data, not generated data. After training the latent feature matrix based solely on known data in the first layer, generated data is selected. Therefore, the generated data set Ω in the first layer is empty.)

[0112] Example 2

[0113] In the above embodiments, a method is provided. Accordingly, the present application also provides an apparatus. The apparatus provided in the embodiments of the present application can implement the above methods. The apparatus can be implemented through software, hardware, or a combination of software and hardware. For example, the apparatus can include integrated or separate functional modules or units to perform the corresponding steps in each of the above methods.

[0114] In some implementations of the embodiments of the present application, the device 10 provided in the embodiments of the present application is based on the same inventive concept as the method provided in the aforementioned embodiments of the present application and has the same beneficial effects.

[0115] Please refer to Figure 2 , which shows a schematic diagram of a device provided by some embodiments of the present application. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple. For relevant details, please refer to the partial description of the method embodiments. The device embodiments described below are merely illustrative.

[0116] like Figure 2 As shown, the apparatus 10 may include:

[0117] The citation network known data acquisition module 110 is used to acquire the original citation network known data;

[0118] The citation network author relationship tensor construction module 120 is used to construct the citation network author relationship tensor and the latent feature matrix of the multi-layer citation network author link based on the original citation network known data;

[0119] A citation network training module 130 is configured to construct a target loss function for citation network author relationship prediction based on the citation network author relationship tensor, train the latent feature matrix of each layer of citation network author links using the target loss function, and iteratively optimize the target loss function;

[0120] The citation network author relationship link prediction module 140 is used to obtain the prediction result of the citation network author relationship link based on the trained latent feature matrix of each layer of the citation network author link.

[0121] Among them, the citation network training module 130 includes an initialization unit 131 and a training unit 132; the initialization unit 131 is used to initialize the process parameters involved in the citation network author relationship link prediction process; the training unit 132 is used to combine the constructed citation network author relationship tensor and the relevant parameters involved in the citation network author relationship link prediction process initialized by the initialization unit 131 to perform each layer of training to calculate the latent feature matrix of the historical citation network author relationship link.

[0122] The citation network author relationship link prediction module 140 includes a citation network data generation unit 141, a citation network author relationship link prediction value calculation unit 142, and a citation network generated data storage unit 143. The citation network author relationship link prediction value calculation unit 140 is used to select new citation network generated data based on the latent feature matrix of historical citation network author relationship links obtained by the training unit 132, using the data generation unit 141. The citation network author relationship link prediction value calculation unit 142 calculates the citation network author relationship link prediction value, and performs nonlinear activation on the value. Finally, the predicted value and the corresponding author pair are stored in the citation network generated data storage unit 142.

[0123] The iterative optimization process and parameter-related definitions involved in this embodiment have been explained in the previous embodiments and will not be repeated here.

[0124] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0128] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0129] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and description of the present application.

Claims

1. A method for predicting author collaboration links in citation networks based on multi-layer predictive sampling, characterized by: The steps include: S1: Obtain known data of the original citation network; S2: Based on the known data of the original citation network, construct the citation network author relationship tensor and the latent feature matrix of the multi-layer citation network author links; S3: Based on the citation network author relationship tensor, construct a target loss function for citation network author relationship prediction, use the target loss function to train the latent feature matrix of each layer of citation network author links, and iteratively optimize the target loss function; S4: Based on the latent feature matrix of the author links in each layer of the citation network after training, the prediction results of the author relationship links in the citation network are obtained; The known data of the citation network is stored in the form of a quadruple, which is represented by W = (a1, a2, rel, l); a1 and a2 represent different authors in the citation network, rel represents the meta-path relationship between author a1 and author a2, and l represents the relationship link value of the author collaboration between author a1 and author a2 through the meta-path relationship rel; Step S2 includes: S21: Divide all the quadruple W=(a1, a2, rel, l) in the known data of the citation network into K time period data according to the meta-path relationship rel; S22: Quadruple W based on rel=1 (1) =(a1,a2,1,l) to get W (1) Data (a1, a2, l), and according to W (1) Construct a slice matrix T with element path relation rel=1 (1) ; S23: Select the quadruple W from the quadruple W = (a1, a2, rel, l) in sequence based on the above steps according to the remaining meta-path relations rel (2) 、W (3) ,…,W (K) , respectively construct the slice matrix T (2) 、T (3) ,…,T (K) ; S24: Arrange the K slice matrices in ascending order according to the order of the divided meta-path relationships to construct a citation network author relationship tensor Y; S25: Based on the known data of the citation network, construct the latent feature matrices G, D, and Q of the author links of the multi-layer citation network; Among them, the citation network tensor Y is constructed based on the known data set Ψ and the generated data set Ω to construct the target loss function ε, which is expressed by the following formula: Among them, n represents the number of layers; G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer respectively; Represents the single element value corresponding to the latent feature matrix of the nth layer; α and β represent weights; y ijk represents a known entity in the author relationship tensor Y of the citation network, i.e., the value of the collaborative relationship link between the i-th author and the j-th author on the k-th relationship; Represents the predicted value corresponding to the generated data selected layer by layer and the final predicted value obtained by the nonlinear activation function; the slice matrix T (1) The size of the slice matrix T is I rows and J columns, where I and J are the number of authors, K is a positive integer, and (1) The element T in (1) ij Indicates the relationship link value between the i-th author and the j-th author under the first relationship, 1≤i≤I, 1≤j≤J, Represents a set of real numbers; where the size of the latent feature matrix G is I rows and R columns, the size of the latent feature matrix D is J rows and R columns, and the size of the latent feature matrix Q is K rows and R columns.

2. The method according to claim 1, characterized in that Step S3 includes: S31: Initialize the process parameters involved in the prediction of author relationship links in the citation network; S32: Based on the citation network author relationship tensor Y and the latent feature matrices G, D, and Q of the multi-layer citation network author links, a target loss function for citation network author relationship link prediction is constructed; S33: using the target loss function to train the latent feature matrix of the author links in each layer of the citation network and iteratively optimize the target loss function; S34: Determine whether the target loss function satisfies the iteration termination condition. If so, terminate the iteration and output the target loss function as the target loss function after iterative optimization; if not, continue the iteration.

3. The method according to claim 2, characterized in that The process parameters include: citation network author relationship tensor Y, latent feature matrices G, D, Q; rank R that determines the dimension of the latent feature space of the latent feature matrices G, D, Q; number of sampling layers N; maximum number of training iterations max Round; a variable round that controls the number of iterations of the training process; and a convergence termination threshold τ.

4. The method according to claim 3, characterized in that Step S32 includes: S321: Traverse the multi-layer sampling layer number n∈{1,…,N}, and use the target loss function to train and obtain the latent feature matrix G of the author connection of each layer of the citation network constructed for each layer of the citation network author relationship tensor Y and the process parameters. n ,D n ,Q n ; S322: Iteratively optimize the target loss function using the Euclidean distance as the optimization target.

5. The method according to claim 4, characterized in that Step S322 is to use the SGD algorithm to calculate the latent feature matrix G of the nth layer. n ,D n ,Q n Training iterations, including: (1) Fixed D n and Q n , train G through formula (1) n : (2) Fixed G n and Q n , train D by formula (2) n : (3) Fixed G n and D n , train Q by formula (3) n : Among them, ← is the assignment operation, G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer, Represents the hidden feature matrix G of the nth layer respectively n ,D n ,Q n The corresponding single element, η is the learning rate, n is the number of sampling layers; y ijk represents the relationship link value of the collaboration between the i-th author and the j-th author on the k-th meta-path relationship in the citation network author relationship tensor Y; represents the final predicted value of the citation network generated data; Among them, the target loss function ε is the instantaneous loss of a single element in the case of known data and generated data in the citation network at the nth layer by the following formula: Among them, α and β represent weights, For unknown author g i In the corresponding meta-path relation q k Next link author d j The relationship link prediction value is expressed by the following formula:

6. The method according to claim 5, characterized in that The iteration termination condition of step S34 is that the iteration round control variable round reaches the maximum training iteration round number maxRound or the difference between the prediction result of the citation network after the end of the current iteration and the prediction result of the citation network after the end of the current iteration is less than the convergence termination threshold τ.

7. The method according to claim 6, characterized in that The step S4 comprises: The K slice matrices formed by dividing the citation network author relationship tensor Y are sequentially traversed in each row, and a blank position is randomly selected from the known data of the two citation networks to predict the unknown author relationship and obtain the relationship connection prediction value. The relationship link prediction value is then mapped through a nonlinear activation function to obtain the final prediction value; Continuously select new unknown author relationships by slice and row order and repeat the above steps until the preset conditions are met. All the final prediction values and their unknown author relationships are used to generate citation network data. Among them, the relationship connection prediction value is mapped by a nonlinear activation function as follows: The preset condition is that the amount of data generated by the citation network is the same as the amount of data known in the citation network.

8. A citation network author collaboration link prediction device based on multi-layer prediction sampling, characterized in that: include: A citation network known data acquisition module is used to acquire original citation network known data; the citation network known data is stored in the form of a four-tuple, and the four-tuple is represented as W = (a1, a2, rel, l); a1 and a2 respectively represent different authors in the citation network, rel represents the meta-path relationship between author a1 and author a2, and l represents the relationship link value of the author collaboration between author a1 and author a2 through the meta-path relationship rel; The citation network author relationship tensor construction module is used to divide all the four-tuples W = (a1, a2, rel, l) in the known data of the citation network into K time period data according to the meta-path relationship rel; based on the four-tuple W of rel = 1 (1) =(a1,a2,1,l) to get W (1) Data (a1, a2, l), and according to W (1) Construct a slice matrix T with element path relation rel=1 (1) ; According to the remaining meta-path relations rel, the quadruple W is selected from the quadruple W = (a1, a2, rel, l) in turn based on the above steps. (2) 、W (3) ,…,W (K) , respectively construct the slice matrix T (2) 、T (3) ,…,T (K) Arrange the K slice matrices in ascending order according to the order of the divided meta-path relationships to construct a citation network author relationship tensor Y; construct latent feature matrices G, D, and Q of the multi-layer citation network author link based on the known data of the citation network; a citation network training module, configured to construct a target loss function for citation network author relationship prediction based on the citation network author relationship tensor, train the latent feature matrix of each layer of citation network author links using the target loss function, and iteratively optimize the target loss function; for constructing a target loss function for citation network author relationship prediction based on the citation network author relationship tensor, using the target loss function to train the latent feature matrix of each layer of citation network author links and iteratively optimize the target loss function; The citation network author relationship link prediction module is used to obtain the prediction results of the citation network author relationship link based on the trained latent feature matrix of each layer of the citation network author link; Among them, the citation network tensor Y is constructed based on the known data set Ψ and the generated data set Ω to construct the target loss function ε, which is expressed by the following formula: Among them, n represents the number of layers; G n ,D n ,Q n Represent the hidden feature matrix corresponding to the nth layer respectively; Represents the single element value corresponding to the latent feature matrix of the nth layer; α and β represent weights; y ijk represents a known entity in the author relationship tensor Y of the citation network, i.e., the value of the collaborative relationship link between the i-th author and the j-th author on the k-th relationship; Represents the predicted value corresponding to the generated data selected layer by layer and the final predicted value obtained by the nonlinear activation function; the slice matrix T (1) The size of the slice matrix T is I rows and J columns, where I and J are the number of authors, K is a positive integer, and (1) The element T in (1) ij Indicates the relationship link value between the i-th author and the j-th author under the first relationship, 1≤i≤I, 1≤j≤J, Represents a set of real numbers; where the size of the latent feature matrix G is I rows and R columns, the size of the latent feature matrix D is J rows and R columns, and the size of the latent feature matrix Q is K rows and R columns.

Images