Multi-label data clustering segmentation method, system and device based on federated learning and storage medium

Abstract

The invention discloses a multi-label data clustering segmentation method, system and device based on federated learning and a storage medium, a central server extracts image features from an original multi-label data set, the image features and multi-label information of an image are spliced into a feature vector, the central server performs clustering processing on the multi-label data set according to the feature vector, and the clustering processing is performed on the multi-label data set according to the feature vector; and according to the distribution type set by the global parameters, the clustering result and the number of federated clients, dividing the data set into data following the distribution type, and distributing the data to each federated client. And performing image preprocessing on the data of each client, segmenting the data into a training set and a test set, storing configuration information and dividing the training set and the test set, and completing multi-label data clustering segmentation. According to the method, a multi-label classification task is simulated for federated learning through a clustering algorithm, various data distribution conditions required by an experiment are provided, and an effective solution is provided for processing a data segmentation problem of a multi-label data set in federated learning.

Description

Technical Field

[0001] The present invention relates to the field of distributed machine learning technology, and in particular to a multi-label data clustering and segmentation method, system, device and storage medium based on federated learning. Background Art

[0002] Federated learning is a distributed machine learning method that allows multiple devices or servers to collaborate to train a model while protecting their respective local data from being shared. It aims to solve problems such as data privacy and security and data silos. It is particularly suitable for scenarios that process sensitive information, such as privacy identification, medical health, etc., and is a new paradigm in the field of artificial intelligence in recent years.

[0003] However, although federated learning has advantages in privacy protection and data security, it still faces many challenges in practical application, especially when dealing with non-independent and identically distributed (Non-IID) data and multi-label data. Non-IID data may lead to inconsistent performance of federated models and low communication efficiency, and is difficult to optimize. Multi-label data may cause the model to fail to fully utilize the dependencies between labels, which brings additional challenges to model training and aggregation. Currently, the academic community is actively exploring the method design, optimization strategies and communication protocols of federated learning to achieve more efficient, accurate and reliable distributed learning.

[0004] However, the research on federated learning requires comparative experiments on data distributions with different characteristics, and there is a lack of data segmentation methods for multi-label data. Therefore, this scheme proposes a multi-label clustering data segmentation method based on federated learning, which can successfully simulate various data distribution situations in federated learning multi-label classification tasks, and is used to test related federated learning methods to meet the needs of federated learning academic research. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and propose a multi-label data clustering segmentation method, system, device and storage medium based on federated learning. The present invention is aimed at multi-label image datasets and distributes the data to each client according to several data distribution situations in the federated learning multi-label classification task, providing a good environment for experimental verification.

[0006] The objective of the present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a multi-label data clustering segmentation method based on federated learning, the method comprising the following steps:

[0007] S1: The central server loads the original multi-label dataset, uses a convolutional neural network to extract image features, and concatenates them with the original multi-label information of the image into a feature vector;

[0008] S2: The central server performs clustering processing on the feature vectors obtained by splicing the multi-label dataset according to step S1;

[0009] S3: The central server divides the data set into data that follows the distribution type based on the clustering results and distributes it to each federated client according to the distribution type and the number of federated clients set by the global parameters;

[0010] S4: Perform image preprocessing on the data of each federated client, split it into training set and test set, save the configuration information and the division of training set and test set, and complete multi-label data clustering and segmentation.

[0011] Furthermore, in step S1, the central server loads the original multi-label dataset, inputs it into the pre-trained convolutional neural network ResNet to extract image features, and generates feature vectors for each image.

[0012] Furthermore, in step S1, the multi-label data of the image is converted into a multi-label vector in a one-hot encoding form and concatenated with the feature vector of the image to comprehensively represent the visual information and semantic information of the image.

[0013] Furthermore, in step S3, according to the global preset parameters, the clustered data set is divided into subsets with the same number of participating clients according to five different multi-label distribution methods, and assigned to each participating client one by one. The five multi-label distribution methods are: balanced and independent and identically distributed, unbalanced and independent and identically distributed, pathological partitioning, simulated real-life distribution and mixed distribution, and the mixed distribution is a mixture of pathological partitioning and simulated real-life distribution.

[0014] Furthermore, in order to simulate the distribution of real situations, Dirichlet segmentation is performed on the multi-label dataset based on the clustering results to simulate the data distribution in real situations.

[0015] Furthermore, for mixed distribution, a certain proportion of data is divided by simulating the actual distribution and allocated to the corresponding proportion of clients, and the remaining data is divided by mixed pathological partitioning and allocated to the remaining clients. The proportion is set in the global parameters.

[0016] Furthermore, in step S3, the image allocated to each client is preprocessed, including resizing, random cropping, horizontal flipping and normalization operations.

[0017] In a second aspect, the present invention also provides a multi-label data clustering and segmentation system based on federated learning, the system comprising a feature extraction module, a data clustering module, a data segmentation module and a configuration storage module;

[0018] The feature extraction module is used by the central server to extract image features from the multi-label data set and splice them with the original multi-label information of the image into a feature vector;

[0019] The data clustering module is used by the central server to perform clustering processing on the multi-label data set according to the feature vector;

[0020] The data segmentation module is used by the central server to divide the data set into data that follows the distribution type based on the clustering result and distribute it to each federated client according to the distribution type and the number of federated clients set by the global parameters;

[0021] The configuration storage module is used to perform image preprocessing on the data of each client, segment it into a training set and a test set, and save the configuration information and the division of the training set and the test set to complete the multi-label data clustering segmentation.

[0022] In the third aspect, the present invention also provides a multi-label data clustering segmentation device based on federated learning, comprising a memory and one or more processors, wherein the memory stores executable code, and when the processor executes the executable code, it implements the multi-label data clustering segmentation method based on federated learning.

[0023] In a fourth aspect, the present invention further provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the multi-label data clustering and segmentation method based on federated learning.

[0024] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the multi-label data clustering and segmentation method based on federated learning.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. The present invention proposes an original multi-label clustering data segmentation method, which effectively solves the problems of uneven distribution and data heterogeneity faced by the prior art when processing multi-label image data sets. This method not only takes into account the multi-label characteristics of the data set, but also optimizes according to the actual needs and number of clients in the federated learning environment, thereby providing a more accurate and efficient data preprocessing method for federated learning multi-label classification tasks.

[0027] 2. The present invention can simulate different data distribution scenarios in federated learning multi-label classification tasks by segmenting the data set and using probabilistic methods such as Dirichlet distribution, including but not limited to independent and identically distributed / non-independent and identically distributed and balanced / unbalanced distribution in multi-label scenarios. This flexible processing capability enables the present invention to perform customized data preparation for specific federated learning scenarios, greatly improving experimental efficiency.

[0028] 3. Before data segmentation, the central server first performs clustering on the multi-label data set. This step helps to reveal the inherent structure and relationship of the data and improve the efficiency of data utilization. Through clustering preprocessing, it can be ensured that the data set assigned to each client is not only balanced in quantity but also representative in feature space, thereby enhancing the generalization ability of the federated learning model. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 The figure is a flowchart of the overall steps of the multi-label data clustering and segmentation method based on federated learning of the present invention.

[0031] Figure 2 Schematic diagram of data segmentation of the multi-label data clustering segmentation method based on federated learning of the present invention.

[0032] Figure 3 This is a structural diagram of a multi-label data clustering and segmentation device based on federated learning of the present invention. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Federated learning is a privacy-preserving distributed machine learning technology. Each client uses local data to independently train a model, and then only uploads model parameters or model updates to the central server. The central server aggregates these data to update the global model, and then sends the improved model back to each client. In this way, federated learning not only guarantees performance, but also ensures the data security of each client. The present invention proposes a multi-label clustering data segmentation method based on federated learning, which segments the images and labels in the data set according to different distribution types and assigns them to each client, simulating various data distribution situations that may occur in federated learning for academic experiments.

[0035] The multi-label classification task is a machine learning task, which is different from the traditional single-label classification task. Each image can be assigned to multiple labels at the same time, which may cause dependencies between labels and imbalanced label distribution. This makes it a difficult problem to effectively partition the multi-label data set when using federated learning to process multi-label classification tasks. The multi-label data clustering and segmentation method based on federated learning proposed in the present invention first clusters the multi-label data set, and then distributes the data to each client according to different distribution types based on the clustering results, which effectively solves the problem of data allocation when processing multi-label data sets during federated learning training. In addition, in the clustering process, the method introduces a deep learning method, uses a convolutional neural network to extract features from the multi-label data set, incorporates the feature information into the label vector for clustering, and increases the dimension of the data.

[0036] Dirichlet Distribution is a probability distribution that is defined on a k-1 dimensional simplex and is used to describe the probability distribution of k categories / events. In simple terms, it can be seen as a generalization of the Beta distribution in multidimensional space and is used to describe the parameters of multinomial distribution. k Composition, where each α k Corresponding to one dimension or category in the distribution, K is the total number of categories, and these parameters are often called concentration parameters, which affect the shape of the distribution. k >1, the distribution tends to be more uniform; when α k <1, the distribution tends to be more concentrated in one or several dimensions. The Dirichlet distribution has strong flexibility and can simulate distributions of various shapes by adjusting the concentration parameter, and the value of the concentration parameter has an intuitive explanation, so the present invention uses the Dirichlet distribution to simulate non-independent and identically distributed in reality.

[0037] Please combine Figure 1 , Figure 2As shown, the present invention provides a multi-label data clustering segmentation method based on federated learning, comprising the following steps:

[0038] S1: The central server loads the original multi-label dataset, uses a convolutional neural network to extract image features, and concatenates them with the original multi-label information of the image into a feature vector to comprehensively represent the visual and semantic information of the image.

[0039] In step S1, the present invention takes the dataset VPA (a privacy image dataset, each image corresponds to multiple privacy labels, 2017) as an example. The central server first receives a multi-label dataset, which contains a large number of images and their corresponding multiple labels, reads the index file in the dataset (stored in CSV format), and the index file includes the image file name and the label number it has, and reads the corresponding image in the file system according to the file name. Then, the image is cropped to a uniform size and input into the pre-trained ResNet-18 model for image feature extraction. The last fully connected layer is removed, only the feature extraction part is retained, and the feature is flattened into a one-dimensional vector as the image feature vector. In addition, for the label number of each image, one-hot encoding (One-Hot Label) is used for binary conversion to obtain an image label vector. Finally, the image feature vector and the image label vector are spliced ​​and fused into a larger feature vector to expand the dimension of the image data and facilitate clustering processing.

[0040] S2: The central server uses the K-Means algorithm to cluster the feature vectors obtained by splicing the multi-label dataset according to step S1.

[0041] In step S2, the central server needs to perform clustering on the multi-label data set to divide the data subsets for the subsequent federated learning tasks. To this end, the central server first receives the label feature vectors extracted for each sample in step S1, which will serve as the basis for cluster analysis. Taking into account the characteristics of federated learning, the present invention determines the number of clusters K according to the number of clients participating in federated learning, ensuring that each client can receive sufficient and diverse data, thereby improving the model training effect. Subsequently, the central server executes the K-Means clustering algorithm to divide the label feature vectors of all samples into K different clusters. Each cluster represents a specific area in the label space and contains samples with similar label features. According to the clustering results, the central server divides the original multi-label data set into K non-repeating subsets, each of which corresponds to a specific cluster. Finally, the central server stores the clustering results as a CSV file, and adds a column of "clustering category" data to the original index file to record the cluster to which each sample belongs, facilitating the subsequent data allocation and federated learning training process.

[0042] S3: The central server divides the data set to each client according to the clustering results based on the different distribution types set by the parameters.

[0043] In step S3, the central server performs data segmentation on the multi-label data set after label clustering according to the parameters preset by the user, and divides it into several subsets equal to the number of participating federated learning clients according to different multi-label distribution methods, and distributes them to each participating client to simulate several experimental scenarios of federated learning multi-label classification, such as Figure 2 As shown in the figure, "niid", "balance", and "partition" are the parameters set by the user when running the code, which are used to divide the multi-label data set into 5 different data distributions, among which "niid" indicates whether to use non-independent and identical distribution, "balance" indicates whether the amount of data between clients is balanced, and "partition" indicates the specific distribution specified. The 5 distribution types and their corresponding parameters are as follows:

[0044] 1. Balanced and independent and identically distributed (parameters: niid = False, balance = True)

[0045] 2. Unbalanced and independent and identically distributed (parameters: niid = False, balance = False)

[0046] 3. Pathological partition (parameters: niid = True, balance = False, partition = 'cpat')

[0047] 4. Simulate the actual distribution (parameters: niid = True, balance = False, partition = 'cdir')

[0048] 5. Mixed distribution (parameters: niid = True, balance = False, partition = 'chaos')

[0049] For balanced and independent and identically distributed, this is the most ideal data distribution situation. All clients will obtain data from all clusters, ensuring the homogeneity of data distribution (independent and identically distributed), and each client obtains approximately the same samples from each cluster to achieve a balanced amount of data. This setting is used to simulate an ideal federated learning scenario where data is evenly distributed among clients. It helps the model learn effective feature representations, thereby improving classification accuracy and model generalization ability.

[0050] For unbalanced and independent and identically distributed, all clients will still get data from all clusters, the difference is that the number of samples each client gets from each cluster is random, but still within a reasonable range to ensure that each client gets at least a certain number of samples. This setting simulates a more realistic independent and identically distributed scenario, where data is evenly distributed between clients, but the amount of data may vary. The data is independent and identically distributed between clients, but there is an imbalance in the labels, that is, the sample size of some labels is much larger than that of other labels, resulting in the model's weak recognition ability for labels with fewer samples, reducing classification performance.

[0051] For pathological partitioning, each client only obtains data from some clusters, and the number of clusters obtained by each client is controlled by user-set parameters, resulting in heterogeneity in data distribution (non-IID), and each client obtains a random number of samples from its assigned cluster. Each client may have data with only a very small number of labels, and the label distribution is unbalanced, further increasing the heterogeneity of the data volume. This setting is used to simulate non-IID scenarios where data differs significantly between clients, such as different types of data collected by different devices. This is the data distribution that has the greatest impact on model performance. The model may overfit the minority classes on most clients, making it difficult to learn common feature representations, which greatly reduces the performance and generalization ability of the model.

[0052] For the simulated real-world distribution, unlike the previous three cases, the Dirichlet distribution is used to assign the data points in each cluster to each client, which results in each client obtaining data from all clusters, but the number of samples in each cluster is randomly determined according to the Dirichlet distribution, thus forming a more complex non-independent and identically distributed data distribution, which is the closest to the real-world data distribution. This setting is suitable for simulating non-independent and identically distributed scenarios with more diverse data distributions, where the data differences between clients may be more subtle and complex, and the label distribution is unbalanced, reflecting the complexity of the real world, thereby better simulating the distribution of federated data in real situations and helping to study and develop more robust federated learning methods.

[0053] For the mixed distribution, in order to more comprehensively simulate the data heterogeneity of federated learning in the real world, the mixed distribution combines the characteristics of pathological partitioning and simulated real-world distribution. Specifically, the mixed distribution first divides the multi-label dataset into two parts according to the ratio α set by the user. The part with a ratio of α adopts a pathological partitioning strategy. Each client only receives data from a specific cluster, and the number of clusters and the number of samples are controlled by user-set parameters. This extreme partitioning method will significantly increase the heterogeneity of data distribution, and some clients may be extremely lacking in specific label data, simulating a scenario where different devices collect data with obvious differences in data types. The remaining part with a ratio of 1-α adopts a simulated real-world distribution strategy based on Dirichlet distribution. Each client obtains data from all clusters, but the number of samples in each cluster is randomly determined by Dirichlet distribution, making the data distribution more complex and closer to the real situation, simulating a scenario where the data distribution is diverse and the differences between clients are more subtle. By adjusting the ratio α, the mixed distribution can flexibly control the degree of pathological partitioning and simulation of the real-world distribution, thereby simulating a wider range of non-independent and identically distributed scenarios, better reflecting the complexity of federated learning data distribution in the real world, and helping researchers develop more robust and generalized federated learning algorithms.

[0054] S4: Perform image preprocessing on the data of each client, divide it into training set and test set according to a certain ratio, and save the configuration information and the division of training set and test set.

[0055] In step S4, each federated client performs image preprocessing and data enhancement on specific images according to the data set assigned to it, including pixel adjustment, cropping, horizontal flipping, format conversion, normalization, etc., and divides the training set and test set of each client according to the ratio of 3:1. Finally, save the configuration information as a CSV file and save each client data set as an NPZ file for subsequent experiments.

[0056] Corresponding to the embodiment of the multi-label data clustering segmentation method based on federated learning, the present invention also provides an embodiment of a multi-label data clustering segmentation system based on federated learning. The system includes a feature extraction module, a data clustering module, a data segmentation module and a configuration storage module; the implementation process of each module refers to the specific steps of the embodiment of the multi-label data clustering segmentation method.

[0057] The feature extraction module is used by the central server to extract image features in a multi-label data set and concatenate them with the image labels into a feature vector.

[0058] The data clustering module is used for the central server to load the original multi-label data set and perform clustering processing on the multi-label data set according to the feature vector;

[0059] The data segmentation module is used for the central server to segment the data set to each federated client according to the clustering result according to the different distribution types set by the parameters of each federated client;

[0060] The configuration storage module is used to perform image preprocessing on the data of each client, segment it into a training set and a test set, and save the configuration information and the division of the training set and the test set to complete the multi-label data clustering segmentation.

[0061] Corresponding to the aforementioned embodiment of a multi-label data clustering segmentation method based on federated learning, the present invention also provides an embodiment of a multi-label data clustering segmentation device based on federated learning.

[0062] See also Figure 3 A multi-label data clustering segmentation device based on federated learning provided in an embodiment of the present invention includes a memory and one or more processors, wherein the memory stores executable code, and when the processor executes the executable code, it is used to implement a multi-label data clustering segmentation method based on federated learning in the above embodiment.

[0063] An embodiment of a multi-label data clustering and segmentation device based on federated learning provided by the present invention can be applied to any device with data processing capabilities, and the device with data processing capabilities can be a device or apparatus such as a computer. The device embodiment can be implemented through software, or through hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of any device with data processing capabilities in which it is located reading the corresponding computer program instructions in the non-volatile memory into the internal memory for execution. From a hardware perspective, if Figure 3 As shown, it is a hardware structure diagram of a multi-label data clustering and segmentation device based on federated learning provided by the present invention, in which any device with data processing capability is located, except Figure 3 In addition to the processor, memory, network interface, and non-volatile memory shown, any device with data processing capabilities in which the apparatus in the embodiments is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0064] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0065] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present invention. Ordinary technicians in this field can understand and implement it without paying creative work.

[0066] An embodiment of the present invention further provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, a multi-label data clustering and segmentation method based on federated learning in the above embodiment is implemented.

[0067] The computer-readable storage medium may be an internal storage unit of any device with data processing capability described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of any device with data processing capability, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of any device with data processing capability. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capability, and may also be used to temporarily store data that has been output or is to be output.

[0068] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the multi-label data clustering and segmentation method based on federated learning.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-label data clustering and segmentation method based on federated learning, characterized in that: The method comprises the following steps: S1: The central server loads the original multi-label dataset, uses a convolutional neural network to extract image features, and concatenates them with the original multi-label information of the image into a feature vector; S2: The central server performs clustering processing on the feature vectors obtained by splicing the multi-label dataset according to step S1; S3: The central server divides the data set into data that follows the distribution type based on the clustering results and distributes it to each federated client according to the distribution type and the number of federated clients set by the global parameters; S4: Perform image preprocessing on the data of each federated client, split it into training set and test set, save the configuration information and the division of training set and test set, and complete multi-label data clustering and segmentation.

2. The multi-label data clustering segmentation method based on federated learning according to claim 1, characterized in that: In step S1, the central server loads the original multi-label dataset, inputs it into the pre-trained convolutional neural network ResNet to extract image features, and generates feature vectors for each image.

3. The multi-label data clustering segmentation method based on federated learning according to claim 2, characterized in that: In step S1, the multi-label data of the image is converted into a multi-label vector using one-hot encoding and concatenated with the feature vector of the image to comprehensively represent the visual information and semantic information of the image.

4. The multi-label data clustering segmentation method based on federated learning according to claim 1, characterized in that: In step S3, according to the global preset parameters, the clustered data set is divided into subsets with the same number of participating clients according to five different multi-label distribution methods, and assigned to each participating client one by one. The five multi-label distribution methods are: balanced and independent and identically distributed, unbalanced and independent and identically distributed, pathological partitioning, simulated real-life distribution and mixed distribution, and the mixed distribution is a mixture of pathological partitioning and simulated real-life distribution.

5. The multi-label data clustering segmentation method based on federated learning according to claim 4, characterized in that: In order to simulate the distribution of real situations, Dirichlet segmentation is performed on the multi-label dataset based on the clustering results to simulate the data distribution in real situations.

6. The multi-label data clustering segmentation method based on federated learning according to claim 4, characterized in that: For mixed distribution, a certain proportion of data is divided by simulating the actual distribution and allocated to the corresponding proportion of clients, and the remaining data is divided by mixed pathological partitioning and allocated to the remaining clients. The proportion is set in the global parameters.

7. The multi-label data clustering segmentation method based on federated learning according to claim 1, characterized in that: In step S3, the image assigned to each client is preprocessed, including resizing, random cropping, horizontal flipping and normalization operations.

8. A multi-label data clustering and segmentation system based on federated learning, characterized in that: The system includes a feature extraction module, a data clustering module, a data segmentation module and a configuration storage module; The feature extraction module is used by the central server to extract image features from the multi-label data set and splice them with the original multi-label information of the image into a feature vector; The data clustering module is used by the central server to perform clustering processing on the multi-label data set according to the feature vector; The data segmentation module is used by the central server to divide the data set into data that follows the distribution type based on the clustering result and distribute it to each federated client according to the distribution type and the number of federated clients set by the global parameters; The configuration storage module is used to perform image preprocessing on the data of each client, segment it into a training set and a test set, and save the configuration information and the division of the training set and the test set to complete the multi-label data clustering segmentation.

9. A multi-label data clustering and segmentation device based on federated learning, comprising a memory and one or more processors, wherein the memory stores executable code, characterized in that: When the processor executes the executable code, a multi-label data clustering segmentation method based on federated learning is implemented as described in any one of claims 1-7.

10. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, a multi-label data clustering and segmentation method based on federated learning is implemented as described in any one of claims 1 to 7.

Images