Federal learning method and system based on bidirectional feedback knowledge distillation and differential privacy

Abstract

The invention belongs to the field of intelligent transportation, and provides a federated learning method and system based on bidirectional feedback knowledge distillation and differential privacy. Dynamic collaborative optimization of a client and a server is realized by designing a bidirectional feedback mechanism, and a knowledge distillation framework is designed at the client, so that the dynamic collaborative optimization of the client and the server is realized. Local model features in a non-independent identically distributed data environment are respectively extracted, traffic data privacy is protected in combination with an adaptive differential privacy algorithm, knowledge distillation and privacy protection strength is dynamically adjusted by means of a bidirectional feedback mechanism, the balance capability of model performance and privacy protection is remarkably improved, and the service life of a server is prolonged. According to the method, a self-adaptive knowledge distillation fusion strategy based on bidirectional feedback is designed, global model optimization is carried out, prediction precision and communication efficiency in a complex traffic scene are further improved, user privacy leakage is effectively avoided, and precision of a federal learning model and adaptability to the complex traffic scene are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a federated learning method and system based on two-way feedback knowledge distillation and differential privacy. Background Art

[0002] With the rapid development of intelligent transportation, the Internet of Vehicles, as an emerging network paradigm, is gradually becoming an important part of smart cities. The Internet of Vehicles realizes real-time sharing and analysis of data by intelligently connecting vehicles, infrastructure and cloud servers, thereby improving traffic efficiency and enhancing driving safety. However, this highly connected environment also brings severe data privacy and security challenges.

[0003] In the existing technology, the Internet of Vehicles usually adopts distributed machine learning methods represented by federated learning, which completes model training locally and uploads model parameters to the central server for global model aggregation. However, the existing federated learning methods face two key problems. On the one hand, the large amount of traffic data (such as location, speed and driving behavior) generated by vehicles and equipment in the Internet of Vehicles is highly sensitive. If it is directly transmitted to the cloud for model training, it may lead to user privacy leakage and violate increasingly stringent data protection regulations. On the other hand, traditional federated learning alleviates some privacy issues through distributed training, but its model accuracy is insufficient when processing non-independent and identically distributed data, and the trade-off between privacy protection and performance optimization has not been fully resolved.

[0004] Therefore, how to design a federated learning method that can improve model accuracy and adapt to complex traffic scenarios while protecting data privacy has become an urgent problem to be solved. Summary of the invention

[0005] Based on this, the present invention proposes a federated learning method and system based on two-way feedback knowledge distillation and differential privacy. By designing a two-way feedback mechanism, dynamic collaborative optimization of the client and server is realized. On the client, a knowledge distillation framework is designed to extract local model features in a non-independent and identically distributed data environment, and the privacy of traffic data is protected by combining an adaptive differential privacy algorithm. The strength of knowledge distillation and privacy protection is dynamically adjusted based on the two-way feedback mechanism, which significantly improves the balance between model performance and privacy protection. On the server side, an adaptive knowledge distillation fusion strategy based on two-way feedback is designed to perform global model optimization, thereby improving the prediction accuracy and communication efficiency in complex traffic scenarios. The present invention not only effectively avoids user privacy leakage, but also improves the accuracy of the federated learning model and its adaptability to complex traffic scenarios.

[0006] The present invention proposes a federated learning method based on bidirectional feedback knowledge distillation and differential privacy, including: The IoV client obtains local traffic data to generate model gradient optimization parameters based on the knowledge distillation algorithm; Performing privacy enhancement processing on the model gradient optimization parameters according to an adaptive differential privacy algorithm to obtain a basic local model, wherein the adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm, and the two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism, and dynamic collaborative optimization of the client and the server is performed according to the client evaluation mechanism and the server evaluation mechanism; Optimizing a two-way feedback mechanism based on supervised learning, wherein the two-way feedback mechanism optimization is based on evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server, and the evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron; The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation, and then performs adaptive knowledge distillation loss optimization on the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prunes and quantizes the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function of the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model, and the pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the change of the knowledge distillation loss on the Internet of Vehicles server.

[0007] In summary, according to the above-mentioned federated learning method based on two-way feedback knowledge distillation and differential privacy, a two-way feedback mechanism is designed to realize dynamic collaborative optimization of the client and server. On the client side, a knowledge distillation framework is designed to extract local model features in non-independent and identically distributed data environments, and the traffic data privacy is protected by combining an adaptive differential privacy algorithm. The strength of knowledge distillation and privacy protection is dynamically adjusted based on the two-way feedback mechanism, which significantly improves the balance between model performance and privacy protection. On the server side, an adaptive knowledge distillation fusion strategy based on two-way feedback is designed to perform global model optimization, thereby improving the prediction accuracy and communication efficiency in complex traffic scenarios. The present invention not only effectively avoids user privacy leakage, but also improves the accuracy of the federated learning model and its adaptability to complex traffic scenarios.Specifically, the Internet of Vehicles client obtains local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm, which better captures the characteristics of the global data distribution. At the same time, the student model of the Internet of Vehicles client can better adapt to the local specific data characteristics of the client by optimizing the loss related to the hard labels in the local traffic data, reducing the loss of generalization performance caused by non-independent and identically distributed data, thereby avoiding the model bias caused by uneven data distribution. The model gradient optimization parameters are privacy-enhanced according to the adaptive differential privacy algorithm to obtain the basic local model. The adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism. The two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm. The two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism. The client and the server are dynamically coordinated and optimized according to the client evaluation mechanism and the server evaluation mechanism. The adaptive differential privacy algorithm can tailor the privacy protection level according to the specific application environment and requirements, reasonably allocate the privacy budget, and avoid the problem of user privacy leakage. The two-way feedback mechanism realizes dynamic parameter adjustment and continuous performance optimization while protecting user privacy. Combined with the basic weight coefficient and the flexible Sensitivity adjustment factor, while considering the relative proportion of cross entropy loss and knowledge distillation loss, further realizing adaptive optimization, and optimizing the two-way feedback mechanism based on supervised learning. The two-way feedback mechanism optimization is based on the evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server. The evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron. The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation, and then optimizes the adaptive knowledge distillation loss of the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prunes and quantizes the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function of the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of the parameters in the global optimization model. The pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the change of the knowledge distillation loss of the Internet of Vehicles server. The present invention not only effectively avoids user privacy leakage, but also enhances the prediction accuracy of the overall model and the adaptability to complex traffic scenes.

[0008] Furthermore, the Internet of Vehicles client obtains local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm, specifically including: The IoV client obtains local traffic data; Generating a learning hard label according to the local traffic data; Inputting the local traffic data into a vehicle networking client teacher model to generate learning soft labels; Inputting the local traffic data, the learned hard labels and the learned soft labels into a student model of the Internet of Vehicles client to obtain model gradient optimization parameters according to a knowledge distillation algorithm; The outputs of the Internet of Vehicles client teacher model and the Internet of Vehicles client student model are softened and converted into probability outputs, and the probability outputs are specifically as follows: , in, represents the prediction probability of the IoV client teacher model, represents the prediction probability of the student model of the Internet of Vehicles client, Indicates the index number of the sample, represents the output activation function, represents the output of the IoV client teacher model, represents the output of the student model of the Internet of Vehicles client, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates client evaluation feedback; The loss of the knowledge distillation algorithm for the IoV client is as follows: , , , in, represents the total loss of the Internet of Vehicles client, represents the cross entropy loss of the Internet of Vehicles client, represents the knowledge distillation loss of the IoV client, represents the cross entropy loss function, represents learning hard labels, represents the number of samples in the local traffic data, Indicates the index ordinal number of the target category, represents the KL divergence.

[0009] Furthermore, the step of performing privacy enhancement processing on the model gradient optimization parameters according to the adaptive differential privacy algorithm specifically includes: Gaussian noise is added to the model gradient optimization parameters according to the adaptive differential privacy algorithm, and the Gaussian noise is adaptively adjusted. The specific algorithm for adding Gaussian noise is as follows: , , in, represents the model gradient after adding Gaussian noise, represents the model gradient, represents the batch size, Indicates that the batch size is A batch is randomly selected from represents the model gradient after clipping, represents Gaussian noise, Indicates the current The noise parameters of the wheel, represents the reference noise parameter, represents the noise adjustment factor, represents the clipping threshold, represents the noise gain factor, Indicates client evaluation feedback, and They represent the consumed differential privacy budget and total privacy budget respectively.

[0010] Furthermore, the two-way feedback mechanism specifically includes: The two-way feedback mechanism includes the client evaluation mechanism and the server evaluation mechanism; The client evaluation mechanism includes an adaptive differential privacy-knowledge distillation feedback path and a knowledge distillation-adaptive differential privacy feedback path; The adaptive differential privacy-knowledge distillation feedback path dynamically adjusts the temperature parameter of the knowledge distillation algorithm according to the performance impact of the adaptive differential privacy algorithm, and the adjustment goal of the temperature parameter is to maximize the adaptation of non-independent and identically distributed; The knowledge distillation-adaptive differential privacy feedback path adjusts the Gaussian noise parameters of the adaptive differential privacy algorithm according to the performance impact of the knowledge distillation algorithm, and the adjustment goal of the Gaussian noise parameters is to ensure the privacy of client data; The specific algorithm of the client evaluation mechanism is as follows: in, Indicates client evaluation feedback, , , , They represent the weights of different evaluation indicators of the client, represents the gradient change evaluation index, represents the loss change evaluation index, represents the training time efficiency, represents the privacy utility balance indicator, represents the L2 norm of the gradient of the current communication round, represents the moving average of the L2 norm of the gradient in the previous communication round, represents the loss ratio, , They represent the actual training time and the estimated training time of the client, respectively. and They represent the consumed differential privacy budget and total privacy budget respectively, represents the maximum value of the noise parameter, represents the noise parameter of round t-1; The specific algorithm of the server evaluation mechanism is as follows: in, Indicates server evaluation feedback. , , Respectively represent the weights of different evaluation indicators on the server side, represents the model accuracy index, represents the communication efficiency index, represents the client participation evaluation indicator, Indicates the accuracy of the global model in the current round in the validation set, represents the target accuracy, Indicates the current communication round, represents the total communication rounds, Indicates the number of clients participating in the current round, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client. Indicates the maximum value of the client evaluation feedback.

[0011] Furthermore, the step of obtaining the basic local models of multiple Internet of Vehicles clients and performing weighted average aggregation on the Internet of Vehicles server side specifically includes: The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation. The specific algorithm of the weighted average aggregation is as follows: , in, represents the global model parameters of the weighted average aggregation, Indicates the current communication round, Represents the basic local model parameters of the Internet of Vehicles client, Indicates The data weight of each client, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client.

[0012] Furthermore, the step of optimizing the adaptive knowledge distillation loss of the Internet of Vehicles server according to the two-way feedback mechanism specifically includes: On the IoV server side, adaptive knowledge distillation loss optimization is performed based on a two-way feedback mechanism; The adaptive knowledge distillation loss optimization is composed of a weighted combination of cross entropy loss and knowledge distillation loss. The weight coefficient in the weighted combination is dynamically adjusted according to the server evaluation feedback. The dynamic adjustment is based on the basic weight coefficient and the sensitivity adjustment factor to adjust the relative proportion of the cross entropy loss and the knowledge distillation loss to complete the adaptive knowledge distillation. The temperature parameter of the adaptive knowledge distillation is dynamically adjusted based on the evaluation feedback and the initial threshold. The client selection threshold is adaptively updated and selected based on the exponential function for the evaluation feedback and the initial threshold. The client selection threshold represents the upper limit of the number of Internet of Vehicles clients selected by the Internet of Vehicles server for weighted average aggregation. The specific algorithm of adaptive knowledge distillation loss on the IoV server side is as follows: , in, represents the total loss of the Internet of Vehicles server, represents the cross entropy loss of the Internet of Vehicles server, represents the knowledge distillation loss of the Internet of Vehicles server, represents the adaptive weight coefficient of knowledge distillation loss, represents the basic weight coefficient, represents the sensitivity adjustment factor, Indicates server evaluation feedback; Feedback adjustment is performed on the adaptive knowledge distillation of the Internet of Vehicles server and the selection threshold of the Internet of Vehicles client. The specific algorithm of the feedback adjustment is as follows: in, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates the selection threshold of the Internet of Vehicles client, represents the initial selection threshold, Indicates the threshold adjustment coefficient.

[0013] Furthermore, the step of obtaining the global optimization model further includes: The IoV server calculates the privacy overhead and checks the privacy budget; It is determined whether the privacy overhead is greater than the privacy budget. If the privacy overhead is greater than the privacy budget, the training cycle of the global optimization model is terminated, and the client and the server are adjusted respectively according to the two-way feedback mechanism.

[0014] The present invention proposes a federated learning system based on bidirectional feedback knowledge distillation and differential privacy, comprising: The client distillation module is used by the IoV client to obtain local traffic data to generate model gradient optimization parameters based on the knowledge distillation algorithm; A differential privacy module, used to perform privacy enhancement processing on the model gradient optimization parameters according to an adaptive differential privacy algorithm to obtain a basic local model, wherein the adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm, and the two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism, and dynamic collaborative optimization of the client and the server is performed according to the client evaluation mechanism and the server evaluation mechanism; A two-way feedback optimization module, which is used to optimize the two-way feedback mechanism based on supervised learning, wherein the two-way feedback mechanism optimization is based on evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server, and the evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron; The server-side distillation module is used for the Internet of Vehicles server to obtain the basic local models of multiple Internet of Vehicles clients and perform weighted average aggregation, and then perform adaptive knowledge distillation loss optimization on the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prune and quantize the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function on the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model, and the pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the changes in the knowledge distillation loss on the Internet of Vehicles server.

[0015] The present invention also provides a storage medium, which stores one or more programs, and when the programs are executed by a processor, implement the above-mentioned federated learning method based on bidirectional feedback knowledge distillation and differential privacy.

[0016] The present invention also provides a computer device, the computer device comprising a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the above-mentioned federated learning method based on bidirectional feedback knowledge distillation and differential privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a federated learning method based on bidirectional feedback knowledge distillation and differential privacy proposed in the first embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a federated learning system based on bidirectional feedback knowledge distillation and differential privacy proposed in the second embodiment of the present invention; Figure 3 A federated learning framework diagram of a federated learning method based on bidirectional feedback knowledge distillation and differential privacy proposed in the first embodiment of the present invention; Figure 4 A diagram of a bidirectional feedback mechanism of a federated learning method based on bidirectional feedback knowledge distillation and differential privacy proposed in the first embodiment of the present invention; Figure 5 This is a framework diagram of the knowledge distillation framework of the Internet of Vehicles client based on the federated learning method with bidirectional feedback knowledge distillation and differential privacy proposed in the first embodiment of the present invention.

[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] See also Figure 1 , which is a flow chart of a federated learning method based on bidirectional feedback knowledge distillation and differential privacy proposed in the first embodiment of the present invention. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy includes steps S01 to S04, wherein: Step S01: The Internet of Vehicles client obtains local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm; It should be noted that the knowledge distillation framework of the Internet of Vehicles client in this embodiment is specifically referred to in Figure 5 , the IoV client obtains local traffic data; Generating a learning hard label according to the local traffic data; Inputting the local traffic data into a vehicle networking client teacher model to generate learning soft labels; Inputting the local traffic data, the learned hard labels and the learned soft labels into a student model of the Internet of Vehicles client to obtain model gradient optimization parameters according to a knowledge distillation algorithm; The outputs of the Internet of Vehicles client teacher model and the Internet of Vehicles client student model are softened and converted into probability outputs, and the probability outputs are specifically as follows: , in, represents the prediction probability of the IoV client teacher model, represents the prediction probability of the student model of the Internet of Vehicles client, Indicates the index number of the sample, represents the output activation function, represents the output of the IoV client teacher model, represents the output of the student model of the Internet of Vehicles client, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates client evaluation feedback; The loss of the knowledge distillation algorithm for the IoV client is as follows: , , , in, represents the total loss of the Internet of Vehicles client, represents the cross entropy loss of the Internet of Vehicles client, represents the knowledge distillation loss of the IoV client, represents the cross entropy loss function, represents learning hard labels, represents the number of samples in the local traffic data, Indicates the index ordinal number of the target category, represents the KL divergence.

[0023] Step S02: Perform privacy enhancement processing on the model gradient optimization parameters according to the adaptive differential privacy algorithm to obtain a basic local model; It should be noted that the adaptive differential privacy algorithm and the knowledge distillation algorithm in this embodiment are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm; Gaussian noise is added to the model gradient optimization parameters according to the adaptive differential privacy algorithm, and the Gaussian noise is adaptively adjusted. The specific algorithm for adding Gaussian noise is as follows: , , in, represents the model gradient after adding Gaussian noise, represents the model gradient, represents the batch size, Indicates that the batch size is A batch is randomly selected from represents the model gradient after clipping, represents Gaussian noise, Indicates the current The noise parameters of the wheel, represents the reference noise parameter, represents the noise adjustment factor, represents the clipping threshold, represents the noise gain factor, Indicates client evaluation feedback, and They represent the consumed differential privacy budget and total privacy budget respectively; For details on the bidirectional feedback mechanism in this embodiment, please refer to Figure 4 ; The two-way feedback mechanism includes the client evaluation mechanism and the server evaluation mechanism; The client evaluation mechanism includes an adaptive differential privacy-knowledge distillation feedback path and a knowledge distillation-adaptive differential privacy feedback path; The adaptive differential privacy-knowledge distillation feedback path dynamically adjusts the temperature parameter of the knowledge distillation algorithm according to the performance impact of the adaptive differential privacy algorithm, and the adjustment goal of the temperature parameter is to maximize the adaptation of non-independent and identically distributed; The knowledge distillation-adaptive differential privacy feedback path adjusts the Gaussian noise parameters of the adaptive differential privacy algorithm according to the performance impact of the knowledge distillation algorithm, and the adjustment goal of the Gaussian noise parameters is to ensure the privacy of client data; The specific algorithm of the client evaluation mechanism is as follows: in, Indicates client evaluation feedback, , , , They represent the weights of different evaluation indicators of the client, represents the gradient change evaluation index, represents the loss change evaluation index, represents the training time efficiency, represents the privacy utility balance indicator, represents the L2 norm of the gradient of the current communication round, represents the moving average of the L2 norm of the gradient in the previous communication round, represents the loss ratio, , They represent the actual training time and the estimated training time of the client, respectively. and They represent the consumed differential privacy budget and total privacy budget respectively, represents the maximum value of the noise parameter, represents the noise parameter of round t-1; The specific algorithm of the server evaluation mechanism is as follows: in, Indicates server evaluation feedback. , , Respectively represent the weights of different evaluation indicators on the server side, represents the model accuracy index, represents the communication efficiency index, represents the client participation evaluation indicator, Indicates the accuracy of the global model in the current round in the validation set, represents the target accuracy, Indicates the current communication round, represents the total communication rounds, Indicates the number of clients participating in the current round, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client. Indicates the maximum value of the client evaluation feedback.

[0024] Step S03: Optimizing the two-way feedback mechanism based on supervised learning; It should be noted that the two-way feedback mechanism described in this embodiment optimizes the evaluation indicators and state variables based on the Internet of Vehicles client and the Internet of Vehicles server. The evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron. The multi-layer perceptron maps the input evaluation indicators and state variables to the optimal weights through learnable parameters to achieve dynamic adjustment of the evaluation indicator weights. The specific algorithm for dynamic adjustment of the evaluation indicator weights is as follows: , Represent the weights of the client-side and server-side evaluation indicators, respectively. , Represent the supervised learning multi-layer perceptrons on the client and server, respectively. , Represent the state variables of the client and server respectively, , denote the learnable parameters of the supervised learning multilayer perceptron on the client and server, respectively. , Represent the evaluation indicators of the client and server respectively.

[0025] Step S04: the IoV server obtains the basic local models of multiple IoV clients and performs weighted average aggregation, and then performs adaptive knowledge distillation loss optimization on the IoV server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prunes and quantizes the global optimization model; It should be noted that in this embodiment, the Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation. The specific algorithm of the weighted average aggregation is as follows: , in, represents the global model parameters of the weighted average aggregation, Indicates the current communication round, Represents the basic local model parameters of the Internet of Vehicles client, Indicates The data weight of each client, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client; The weighted average aggregation algorithm in this embodiment is based on the federated learning framework. For the specific architecture of the federated learning framework, please refer to Figure 3 ; On the IoV server side, adaptive knowledge distillation loss optimization is performed based on a two-way feedback mechanism; The adaptive knowledge distillation loss optimization is composed of a weighted combination of cross entropy loss and knowledge distillation loss. The weight coefficient in the weighted combination is dynamically adjusted according to the server evaluation feedback. The dynamic adjustment is based on the basic weight coefficient and the sensitivity adjustment factor to adjust the relative proportion of the cross entropy loss and the knowledge distillation loss to complete the adaptive knowledge distillation. The temperature parameter of the adaptive knowledge distillation is dynamically adjusted based on the evaluation feedback and the initial threshold. The client selection threshold is adaptively updated and selected based on the exponential function for the evaluation feedback and the initial threshold. The client selection threshold represents the upper limit of the number of Internet of Vehicles clients selected by the Internet of Vehicles server for weighted average aggregation. The specific algorithm of adaptive knowledge distillation loss on the IoV server side is as follows: , in, represents the total loss of the Internet of Vehicles server, represents the cross entropy loss of the Internet of Vehicles server, represents the knowledge distillation loss of the Internet of Vehicles server, represents the adaptive weight coefficient of knowledge distillation loss, represents the basic weight coefficient, represents the sensitivity adjustment factor, Indicates server evaluation feedback; Feedback adjustment is performed on the adaptive knowledge distillation of the Internet of Vehicles server and the selection threshold of the Internet of Vehicles client. The specific algorithm of the feedback adjustment is as follows: in, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates the selection threshold of the Internet of Vehicles client, represents the initial selection threshold, represents the threshold adjustment coefficient; The dynamic pruning and quantization described in this embodiment are driven by knowledge distillation. A parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function on the Internet of Vehicles server side. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model. The pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation index in the two-way feedback mechanism. The quantization step size is dynamically adjusted based on the change of the knowledge distillation loss on the Internet of Vehicles server side. Pruning is used to remove parameters that have little contribution or influence on the knowledge distillation process. Quantization is used to convert model parameters from high precision to low precision to reduce storage and transmission requirements. The specific algorithm of dynamic pruning and quantization in this embodiment is as follows: in, represents the parameter importance evaluation matrix, represents the knowledge distillation loss of the Internet of Vehicles server, represents the squared expected value of the global optimization model parameters, represents the pruning rate, represents the maximum pruning rate, represents the sensitivity of pruning rate, represents the model accuracy index, represents the communication efficiency index, represents the client participation evaluation indicator, represents the global optimization model parameters, Indicates the quantization bit width, represents the quantization step size, represents the basic quantization step size, Indicates the current communication round; The IoV server calculates the privacy overhead and checks the privacy budget; It is determined whether the privacy overhead is greater than the privacy budget. If the privacy overhead is greater than the privacy budget, the training cycle of the global optimization model is terminated, and the client and the server are adjusted respectively according to the two-way feedback mechanism.

[0026] In summary, according to the above-mentioned federated learning method based on two-way feedback knowledge distillation and differential privacy, a two-way feedback mechanism is designed to realize dynamic collaborative optimization of the client and server. On the client side, a knowledge distillation framework is designed to extract local model features in non-independent and identically distributed data environments, and the traffic data privacy is protected by combining an adaptive differential privacy algorithm. The strength of knowledge distillation and privacy protection is dynamically adjusted based on the two-way feedback mechanism, which significantly improves the balance between model performance and privacy protection. On the server side, an adaptive knowledge distillation fusion strategy based on two-way feedback is designed to perform global model optimization, thereby improving the prediction accuracy and communication efficiency in complex traffic scenarios. The present invention not only effectively avoids user privacy leakage, but also improves the accuracy of the federated learning model and its adaptability to complex traffic scenarios.Specifically, the Internet of Vehicles client obtains local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm, which better captures the characteristics of the global data distribution. At the same time, the student model of the Internet of Vehicles client can better adapt to the local specific data characteristics of the client by optimizing the loss related to the hard labels in the local traffic data, reducing the loss of generalization performance caused by non-independent and identically distributed data, thereby avoiding the model bias caused by uneven data distribution. The model gradient optimization parameters are privacy-enhanced according to the adaptive differential privacy algorithm to obtain the basic local model. The adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism. The two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm. The two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism. The client and the server are dynamically coordinated and optimized according to the client evaluation mechanism and the server evaluation mechanism. The adaptive differential privacy algorithm can tailor the privacy protection level according to the specific application environment and requirements, reasonably allocate the privacy budget, and avoid the problem of user privacy leakage. The two-way feedback mechanism realizes dynamic parameter adjustment and continuous performance optimization while protecting user privacy. Combined with the basic weight coefficient and the flexible Sensitivity adjustment factor, while considering the relative proportion of cross entropy loss and knowledge distillation loss, further realizing adaptive optimization, and optimizing the two-way feedback mechanism based on supervised learning. The two-way feedback mechanism optimization is based on the evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server. The evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron. The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation, and then optimizes the adaptive knowledge distillation loss of the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prunes and quantizes the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function of the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of the parameters in the global optimization model. The pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the change of the knowledge distillation loss of the Internet of Vehicles server. The present invention not only effectively avoids user privacy leakage, but also enhances the prediction accuracy of the overall model and the adaptability to complex traffic scenes.

[0027] See also Figure 2 , which is a schematic diagram of the structure of a federated learning system based on bidirectional feedback knowledge distillation and differential privacy proposed in the second embodiment of the present invention, and the system includes: The client distillation module 10 is used for the IoV client to obtain local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm; A differential privacy module 20 is used to perform privacy enhancement processing on the model gradient optimization parameters according to an adaptive differential privacy algorithm to obtain a basic local model, wherein the adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm, and the two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism, and dynamic collaborative optimization of the client and the server is performed according to the client evaluation mechanism and the server evaluation mechanism; A two-way feedback optimization module 30, for optimizing a two-way feedback mechanism based on supervised learning, wherein the two-way feedback mechanism optimization is based on evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server, wherein the evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron; The server-side distillation module 40 is used for the Internet of Vehicles server to obtain the basic local models of multiple Internet of Vehicles clients and perform weighted average aggregation, and then perform adaptive knowledge distillation loss optimization on the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prune and quantize the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function on the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model, and the pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the changes in the knowledge distillation loss on the Internet of Vehicles server.

[0028] The present invention also proposes a computer storage medium on which one or more programs are stored, which, when executed by a processor, implement the above-mentioned federated learning method based on bidirectional feedback knowledge distillation and differential privacy.

[0029] The present invention also proposes a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so as to implement the above-mentioned federated learning method based on bidirectional feedback knowledge distillation and differential privacy.

[0030] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain storage, communication, propagation or transmission of a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0031] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0032] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0033] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0034] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A federated learning method based on bidirectional feedback knowledge distillation and differential privacy, characterized in that: include: The IoV client obtains local traffic data to generate model gradient optimization parameters based on the knowledge distillation algorithm; Performing privacy enhancement processing on the model gradient optimization parameters according to an adaptive differential privacy algorithm to obtain a basic local model, wherein the adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm, and the two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism, and dynamic collaborative optimization of the client and the server is performed according to the client evaluation mechanism and the server evaluation mechanism; Optimizing a two-way feedback mechanism based on supervised learning, wherein the two-way feedback mechanism optimization is based on evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server, and the evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron; The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation, and then performs adaptive knowledge distillation loss optimization on the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prunes and quantizes the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function of the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model, and the pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the change of the knowledge distillation loss on the Internet of Vehicles server.

2. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The Internet of Vehicles client obtains local traffic data to generate model gradient optimization parameters according to the knowledge distillation algorithm, specifically including: The IoV client obtains local traffic data; Generating a learning hard label according to the local traffic data; Inputting the local traffic data into a vehicle networking client teacher model to generate learning soft labels; Inputting the local traffic data, the learned hard labels and the learned soft labels into a student model of the Internet of Vehicles client to obtain model gradient optimization parameters according to a knowledge distillation algorithm; The outputs of the Internet of Vehicles client teacher model and the Internet of Vehicles client student model are softened and converted into probability outputs, and the probability outputs are specifically as follows: ， in, represents the prediction probability of the IoV client teacher model, represents the prediction probability of the student model of the Internet of Vehicles client, Indicates the index number of the sample, represents the output activation function, represents the output of the IoV client teacher model, represents the output of the student model of the Internet of Vehicles client, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates client evaluation feedback; The loss of the knowledge distillation algorithm for the IoV client is as follows: ， ， ， in, represents the total loss of the Internet of Vehicles client, represents the cross entropy loss of the Internet of Vehicles client, represents the knowledge distillation loss of the Internet of Vehicles client, represents the cross entropy loss function, represents learning hard labels, represents the number of samples in the local traffic data, Indicates the index ordinal number of the target category, represents the KL divergence.

3. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The step of performing privacy enhancement processing on the model gradient optimization parameters according to the adaptive differential privacy algorithm specifically includes: Gaussian noise is added to the model gradient optimization parameters according to the adaptive differential privacy algorithm, and the Gaussian noise is adaptively adjusted. The specific algorithm for adding Gaussian noise is as follows: ， ， in, represents the model gradient after adding Gaussian noise, represents the model gradient, represents the batch size, Indicates that the batch size is A batch is randomly selected from represents the model gradient after clipping, represents Gaussian noise, Indicates the current The noise parameters of the wheel, represents the reference noise parameter, represents the noise adjustment factor, represents the clipping threshold, represents the noise gain factor, Indicates client evaluation feedback, and They represent the consumed differential privacy budget and total privacy budget respectively.

4. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The two-way feedback mechanism specifically includes: The two-way feedback mechanism includes the client evaluation mechanism and the server evaluation mechanism; The client evaluation mechanism includes an adaptive differential privacy-knowledge distillation feedback path and a knowledge distillation-adaptive differential privacy feedback path; The adaptive differential privacy-knowledge distillation feedback path dynamically adjusts the temperature parameter of the knowledge distillation algorithm according to the performance impact of the adaptive differential privacy algorithm, and the adjustment goal of the temperature parameter is to maximize the adaptation of non-independent and identically distributed; The knowledge distillation-adaptive differential privacy feedback path adjusts the Gaussian noise parameters of the adaptive differential privacy algorithm according to the performance impact of the knowledge distillation algorithm, and the adjustment goal of the Gaussian noise parameters is to ensure the privacy of client data; The specific algorithm of the client evaluation mechanism is as follows: in, Indicates client evaluation feedback, , , , They represent the weights of different evaluation indicators of the client, represents the gradient change evaluation index, represents the loss change evaluation index, represents the training time efficiency, represents the privacy utility balance indicator, represents the L2 norm of the gradient of the current communication round, represents the moving average of the L2 norm of the gradient in the previous communication round, represents the loss ratio, , They represent the actual training time and the estimated training time of the client, respectively. and They represent the consumed differential privacy budget and total privacy budget respectively, represents the maximum value of the noise parameter, represents the noise parameter of round t-1; The specific algorithm of the server evaluation mechanism is as follows: in, Indicates server evaluation feedback, , , Respectively represent the weights of different evaluation indicators on the server side, represents the model accuracy index, represents the communication efficiency index, represents the client participation evaluation indicator, Indicates the accuracy of the global model in the current round in the validation set, represents the target accuracy, Indicates the current communication round, represents the total communication rounds, Indicates the number of clients participating in the current round, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client. Indicates the maximum value of the client evaluation feedback.

5. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The step of obtaining the basic local models of multiple Internet of Vehicles clients and performing weighted average aggregation on the Internet of Vehicles server specifically includes: The Internet of Vehicles server obtains the basic local models of multiple Internet of Vehicles clients and performs weighted average aggregation. The specific algorithm of the weighted average aggregation is as follows: ， in, represents the global model parameters of the weighted average aggregation, Indicates the current communication round, Represents the basic local model parameters of the Internet of Vehicles client, Indicates The data weight of each client, represents the total number of Internet of Vehicles clients for federated learning, Indicates the ordinal number of the Internet of Vehicles client.

6. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The step of optimizing the adaptive knowledge distillation loss of the Internet of Vehicles server according to the two-way feedback mechanism specifically includes: On the IoV server side, adaptive knowledge distillation loss optimization is performed based on a two-way feedback mechanism; The adaptive knowledge distillation loss optimization is composed of a weighted combination of cross entropy loss and knowledge distillation loss. The weight coefficient in the weighted combination is dynamically adjusted according to the server evaluation feedback. The dynamic adjustment is based on the basic weight coefficient and the sensitivity adjustment factor to adjust the relative proportion of the cross entropy loss and the knowledge distillation loss to complete the adaptive knowledge distillation. The temperature parameter of the adaptive knowledge distillation is dynamically adjusted based on the evaluation feedback and the initial threshold. The client selection threshold is adaptively updated and selected based on the exponential function for the evaluation feedback and the initial threshold. The client selection threshold represents the upper limit of the number of Internet of Vehicles clients selected by the Internet of Vehicles server for weighted average aggregation. The specific algorithm of adaptive knowledge distillation loss on the IoV server side is as follows: ， in, represents the total loss of the Internet of Vehicles server, represents the cross entropy loss of the Internet of Vehicles server, represents the knowledge distillation loss of the Internet of Vehicles server, represents the adaptive weight coefficient of knowledge distillation loss, represents the basic weight coefficient, represents the sensitivity adjustment factor, Indicates server evaluation feedback; Feedback adjustment is performed on the adaptive knowledge distillation of the Internet of Vehicles server and the selection threshold of the Internet of Vehicles client. The specific algorithm of the feedback adjustment is as follows: in, Indicates the current The temperature parameters of the wheel, represents the reference temperature parameter, is the temperature regulation coefficient, Indicates the selection threshold of the Internet of Vehicles client, represents the initial selection threshold, Indicates the threshold adjustment coefficient.

7. The federated learning method based on bidirectional feedback knowledge distillation and differential privacy according to claim 1, characterized in that: The step of obtaining the global optimization model further includes: The IoV server calculates the privacy overhead and checks the privacy budget; It is determined whether the privacy overhead is greater than the privacy budget. If the privacy overhead is greater than the privacy budget, the training cycle of the global optimization model is terminated, and the client and the server are adjusted respectively according to the two-way feedback mechanism.

8. A federated learning system based on two-way feedback knowledge distillation and differential privacy, characterized in that: include: The client distillation module is used by the IoV client to obtain local traffic data to generate model gradient optimization parameters based on the knowledge distillation algorithm; A differential privacy module, used to perform privacy enhancement processing on the model gradient optimization parameters according to an adaptive differential privacy algorithm to obtain a basic local model, wherein the adaptive differential privacy algorithm and the knowledge distillation algorithm are based on a two-way feedback mechanism, and the two-way feedback mechanism is an interactive adjustment cycle between the adaptive differential privacy algorithm and the knowledge distillation algorithm, and the two-way feedback mechanism includes a client evaluation mechanism and a server evaluation mechanism, and dynamic collaborative optimization of the client and the server is performed according to the client evaluation mechanism and the server evaluation mechanism; A two-way feedback optimization module, which is used to optimize the two-way feedback mechanism based on supervised learning, wherein the two-way feedback mechanism optimization is based on evaluation indicators and state variables of the Internet of Vehicles client and the Internet of Vehicles server, and the evaluation indicators and state variables are used to dynamically adjust the evaluation indicator weights of the Internet of Vehicles client and the server in the two-way feedback mechanism through a multi-layer perceptron; The server-side distillation module is used for the Internet of Vehicles server to obtain the basic local models of multiple Internet of Vehicles clients and perform weighted average aggregation, and then perform adaptive knowledge distillation loss optimization on the Internet of Vehicles server according to the two-way feedback mechanism to obtain a global optimization model, and dynamically prune and quantize the global optimization model. The dynamic pruning and quantization are driven by knowledge distillation, and a parameter importance evaluation matrix is ​​constructed through the knowledge distillation loss function on the Internet of Vehicles server. The parameter importance evaluation matrix is ​​used to guide the pruning rate and quantization of parameters in the global optimization model, and the pruning rate and quantization bit width are dynamically adjusted according to the server-side evaluation indicators in the two-way feedback mechanism, and the quantization step size is dynamically adjusted based on the changes in the knowledge distillation loss on the Internet of Vehicles server.

9. A storage medium, characterized in that: The storage medium stores one or more programs, which, when executed by the processor, implement the federated learning method based on bidirectional feedback knowledge distillation and differential privacy as described in any one of claims 1-7.

10. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein: The memory is used to store computer programs; When the processor is used to execute the computer program stored in the memory, it implements the federated learning method based on bidirectional feedback knowledge distillation and differential privacy as described in any one of claims 1-7.

Images