With the rapid development of artificial intelligence and Internet of Things technologies,video action recognition technology is widely applied in various scenarios,such as personal life and industrial production.Howe...With the rapid development of artificial intelligence and Internet of Things technologies,video action recognition technology is widely applied in various scenarios,such as personal life and industrial production.However,while enjoying the convenience brought by this technology,it is crucial to effectively protect the privacy of users’video data.Therefore,this paper proposes a video action recognition method based on personalized federated learning and spatiotemporal features.Under the framework of federated learning,a video action recognition method leveraging spatiotemporal features is designed.For the local spatiotemporal features of the video,a new differential information extraction scheme is proposed to extract differential features with a single RGB frame as the center,and a spatialtemporal module based on local information is designed to improve the effectiveness of local feature extraction;for the global temporal features,a method of extracting action rhythm features using differential technology is proposed,and a timemodule based on global information is designed.Different translational strides are used in the module to obtain bidirectional differential features under different action rhythms.Additionally,to address user data privacy issues,the method divides model parameters into local private parameters and public parameters based on the structure of the video action recognition model.This approach enhancesmodel training performance and ensures the security of video data.The experimental results show that under personalized federated learning conditions,an average accuracy of 97.792%was achieved on the UCF-101 dataset,which is non-independent and identically distributed(non-IID).This research provides technical support for privacy protection in video action recognition.展开更多
In federated learning(FL),the distribution of data across different clients leads to the degradation of global model performance in training.Personalized Federated Learning(pFL)can address this problem through global ...In federated learning(FL),the distribution of data across different clients leads to the degradation of global model performance in training.Personalized Federated Learning(pFL)can address this problem through global model personalization.Researches over the past few years have calibrated differences in weights across the entire model or optimized only individual layers of the model without considering that different layers of the whole neural network have different utilities,resulting in lagged model convergence and inadequate personalization in non-IID data.In this paper,we propose model layered optimization for feature extractor and classifier(pFedEC),a novel pFL training framework personalized for different layers of the model.Our study divides the model layers into the feature extractor and classifier.We initialize the model's classifiers during model training,while making the local model's feature extractors learn the representation of the global model's feature extractors to correct each client's local training,integrating the utilities of the different layers in the entire model.Our extensive experiments show that pFedEC achieves 92.95%accuracy on CIFAR-10,outperforming existing pFL methods by approximately 1.8%.On CIFAR-100 and Tiny-ImageNet,pFedEC improves the accuracy by at least 4.2%,reaching 73.02%and 28.39%,respectively.展开更多
Federated learning is an emerging distributed privacypreserving framework in which parties are trained collaboratively by sharing model or gradient updates instead of sharing private data. However, the heterogeneity o...Federated learning is an emerging distributed privacypreserving framework in which parties are trained collaboratively by sharing model or gradient updates instead of sharing private data. However, the heterogeneity of local data distribution poses a significant challenge. This paper focuses on the label distribution skew, where each party can only access a partial set of the whole class set. It makes global updates drift while aggregating these biased local models. In addition, many studies have shown that deep leakage from gradients endangers the reliability of federated learning. To address these challenges, this paper propose a new personalized federated learning method named MpFedcon. It addresses the data heterogeneity problem and privacy leakage problem from global and local perspectives. Our extensive experimental results demonstrate that MpFedcon yields effective resists on the label leakage problem and better performance on various image classification tasks, robust in partial participation settings, non-iid data,and heterogeneous parties.展开更多
Semantic Communication(SemCom)is a promising paradigm for future 6G networks,where communication performance hinges on the effectiveness of SemCom models,particularly the source-channel encoder and decoder.However,tra...Semantic Communication(SemCom)is a promising paradigm for future 6G networks,where communication performance hinges on the effectiveness of SemCom models,particularly the source-channel encoder and decoder.However,training these models faces significant challenges.Firstly,the privacy-sensitive nature of communication data discourages users from uploading data to centralized servers.Secondly,heterogeneous local data distributions and diverse communication counterparts of different users necessitate personalized SemCom models.Specifically,a user's encoder must align with its receivers'decoders and the transmitted data distribution,while its decoder must adapt to the user's transmitters and received data distribution.To address these challenges,we propose FineFed,a personalized federated learning method with collaborative fine-tuning.Initially,a unified global model is trained distributively via federated learning,eliminating data uploads.Subsequently,users iteratively fine-tune encoders and decoders collaboratively,achieving SemCom model personalization.For encoder fine-tuning,decoders are fixed and shared with transmitters to address distributed loss calculation issues.Each encoder is fine-tuned using the idea of multi-task learning,treating communication with each receiver as a separate task.Then,encoders are fixed.A user shares its decoder with its own transmitters.These transmitters collaboratively fine-tune the user's decoder by the idea of federated multitask learning.Experimental results demonstrate that FineFed improves the average performance of federated SemCom models by 1%-7%,bringing it closer to the performance of centrally-trained models.展开更多
Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitiv...Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.展开更多
Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse ...Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse service requirements,6G network architecture should offer personalized services to various mobile devices.Federated learning(FL)with personalized local training,as a privacypreserving machine learning(ML)approach,can be applied to address these challenges.In this paper,we propose a meta-learning-based personalized FL(PFL)method that improves both communication and computation efficiency by utilizing over-the-air computations.Its“pretraining-and-fine-tuning”principle makes it particularly suitable for enabling edge nodes to access personalized GAI services while preserving local privacy.Experiment results demonstrate the outperformance and efficacy of the proposed algorithm,and notably indicate enhanced communication efficiency without compromising accuracy.展开更多
In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide ef...In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide efficient and privacypreserving collaborative learning.However,in Io V environment,federated learning faces the challenges introduced by high mobility of vehicles and nonIndependently Identically Distribution(non-IID)of data.High mobility causes FL clients quit and the communication offline.The non-IID data leads to slow and unstable convergence of global model and single global model's weak adaptability to clients with different localization characteristics.Accordingly,this paper proposes a personalized aggregation strategy for hierarchical Federated Learning in Io V environment,including Fed SA(Special Asynchronous Federated Learning with Self-adaptive Aggregation)for low-level FL between a Road Side Unit(RSU)and the vehicles within its coverage,and Fed Att(Federated Learning with Attention Mechanism)for high-level FL between a cloud server and multiple RSUs.Agents self-adaptively obtain model aggregation weight based on Advantage Actor-Critic(A2C)algorithm.Experiments show the proposed strategy encourages vehicles to participate in global aggregation,and outperforms existing methods in training performance.展开更多
Federated learning(FL)is a promising technique to build a power generation model in photovoltaic(PV)scenarios.However,due to the heterogeneity of power generation data,there is a problem of slow convergence of the glo...Federated learning(FL)is a promising technique to build a power generation model in photovoltaic(PV)scenarios.However,due to the heterogeneity of power generation data,there is a problem of slow convergence of the global model or even deviation from the optimal solution during model training.Therefore,to improve the prediction accuracy and accelerate the model convergence speed,this paper proposes a model functional blocking and differentiated scheduling mechanism under personalized FL framework for intermittent PV power generation.Firstly,cluster analysis is conducted according to longitude,latitude,and altitude to form a model collaborative training region(MCTR).Then,based on the constructed MCTRs,a personalized FL model training method is proposed.This method is based on a combination of global shared convolutional neural network(CNN)model and local personalized long short term memory(LSTM)model,where CNN model block is responsible for feature extraction and LSTM model block is responsible for prediction.It adopts synchronous aggregation for global shared CNN and asynchronous aggregation for personalized LSTM.Furthermore,the FL server performs block scheduling of the CNN-LSTM models and aggregates them based on the regional membership which can provide differentiated and accurate prediction models with different power generation patterns.The simulation results show that the proposed algorithm has the highest accuracy of 85.1%and the best performance on mean absolute error(MAE),root mean square error(RMSE)and mean absolute percentage error(MAPE),with 0.1105,0.1224 and 0.4383 respectively.展开更多
A centralized framework-based data-driven framework for active distribution system state estimation(DSSE)has been widely leveraged.However,it is challenged by potential data privacy breaches due to the aggregation of ...A centralized framework-based data-driven framework for active distribution system state estimation(DSSE)has been widely leveraged.However,it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center.A personalized federated learningbased DSSE method(PFL-DSSE)is proposed in a decentralized training framework for DSSE.Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.展开更多
Most finger vein authentication systems suffer from the problem of small sample size.However,the data augmentation can alleviate this problem to a certain extent but did not fundamentally solve the problem of category...Most finger vein authentication systems suffer from the problem of small sample size.However,the data augmentation can alleviate this problem to a certain extent but did not fundamentally solve the problem of category diversity.So the researchers resort to pre-training or multi-source data joint training methods,but these methods will lead to the problem of user privacy leakage.In view of the above issues,this paper proposes a federated learning-based finger vein authentication framework(FedFV)to solve the problem of small sample size and category diversity while protecting user privacy.Through training under FedFV,each client can share the knowledge learned from its user′s finger vein data with the federated client without causing template leaks.In addition,we further propose an efficient personalized federated aggregation algorithm,named federated weighted proportion reduction(FedWPR),to tackle the problem of non-independent identically distribution caused by client diversity,thus achieving the best performance for each client.To thoroughly evaluate the effectiveness of FedFV,comprehensive experiments are conducted on nine publicly available finger vein datasets.Experimental results show that FedFV can improve the performance of the finger vein authentication system without directly using other client data.To the best of our knowledge,FedFV is the first personalized federated finger vein authentication framework,which has some reference value for subsequent biometric privacy protection research.展开更多
Accurate load forecasting is critical for electricity production,transmission,and maintenance.Deep learning(DL)model has replaced other classical models as the most popular prediction models.However,the deep predictio...Accurate load forecasting is critical for electricity production,transmission,and maintenance.Deep learning(DL)model has replaced other classical models as the most popular prediction models.However,the deep prediction model requires users to provide a large amount of private electricity consumption data,which has potential privacy risks.Edge nodes can federally train a global model through aggregation using federated learning(FL).As a novel distributed machine learning(ML)technique,it only exchanges model parameters without sharing raw data.However,existing forecasting methods based on FL still face challenges from data heterogeneity and privacy disclosure.Accordingly,we propose a user-level load forecasting system based on personalized federated learning(PFL)to address these issues.The obtained personalized model outperforms the global model on local data.Further,we introduce a novel differential privacy(DP)algorithm in the proposed system to provide an additional privacy guarantee.Based on the principle of generative adversarial network(GAN),the algorithm achieves the balance between privacy and prediction accuracy throughout the game.We perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.展开更多
Federated Learning(FL)is a framework for machine learning on a large-scale distributed dataset,enabling the training of a collaborative model across multiple parties while preserving the privacy of user data.However,i...Federated Learning(FL)is a framework for machine learning on a large-scale distributed dataset,enabling the training of a collaborative model across multiple parties while preserving the privacy of user data.However,in cases where data are distributed in a non-independent and identically distributed(non-iid)manner,the convergence speed of the federated collaborative model and its prediction accuracy on client nodes can be significantly affected.Therefore,personalized FL methods have emerged to further adapt to the data characteristics of different clients.In response to the data heterogeneity issue,this paper presents a multi-task clustering-based personalized federated learning algorithm,which is applied to the prediction of carbon emissions in different regions and enterprises.This algorithm partitions nodes with similar data distributions and aggregates local models within the same cluster to form cluster models.It introduces the concept of multitask learning,dividing the lower layers of cluster models into expert layers.These expert layers of different cluster models are then weighted and aggregated for the acquisition of global knowledge.Additionally,adaptive weight is applied to control the aggregation of expert layers,thereby achieving model personalization at the local level.Simulation experiments conducted on carbon emission prediction data demonstrate that the proposed algorithm performs better in various evaluation metrics compared with the Federated Averaging(FedAvg)algorithm and traditional clustering personalized federated learning algorithm.It also exhibits excellent experimental results and performance when dealing with different quantities of heterogeneous data distributions.展开更多
The growth of sensory data is unlocking a wave of intelligent sensing analysis.Currently,personalized Federated Learning(pFL)methods are used in intelligent sensing analysis but overlook two aspects:(1)global model pr...The growth of sensory data is unlocking a wave of intelligent sensing analysis.Currently,personalized Federated Learning(pFL)methods are used in intelligent sensing analysis but overlook two aspects:(1)global model preference,causing poor global model performance for minority classes on sensing device data,and(2)dynamic role differences in each layer of deep neural network.In light of this,we present a novel pFL framework over edge-cloud collaborative network,named pFL-Sensing,for intelligent sensing analysis.Specifically,the sensing device serves as an edge server.Each edge server produces a customized model through model training and model aggregation phases.In model training,we design a loss function to alleviate the issue of the global model preference.In model aggregation,layer aggregation and an Adaptive Weight Calculation(AWC)mechanism are proposed to capture dynamic role differences of model layers.Experimental results demonstrate the effectiveness of pFL-Sensing in intelligent sensing analysis.展开更多
Cross-silo federated learning(FL),which benefits from relatively abundant data and rich computing power,is drawing increasing focus due to the significant transformations that foundation models(FMs)are instigating in ...Cross-silo federated learning(FL),which benefits from relatively abundant data and rich computing power,is drawing increasing focus due to the significant transformations that foundation models(FMs)are instigating in the artificial intelligence field.The intensified data heterogeneity issue of this area,unlike that in cross-device FL,is caused mainly by substantial data volumes and distribution shifts across clients,which requires algorithms to comprehensively consider the personalization and generalization balance.In this paper,we aim to address the objective of generalized and personalized federated learning(GPFL)by enhancing the global model’s cross-domain generalization capabilities and simultaneously improving the personalization performance of local training clients.By investigating the fairness of performance distribution within the federation system,we explore a new connection between generalization gap and aggregation weights established in previous studies,culminating in the fairness-guided federated training for generalization and personalization(FFT-GP)approach.FFT-GP integrates a fairness-aware aggregation(FAA)approach to minimize the generalization gap variance among training clients and a meta-learning strategy that aligns local training with the global model’s feature distribution,thereby balancing generalization and personalization.Our extensive experimental results demonstrate FFT-GP’s superior efficacy compared to existing models,showcasing its potential to enhance FL systems across a variety of practical scenarios.展开更多
Federated learning faces challenges with non-IID data distributions,often resulting in suboptimal performance for individual clients with the global model.To address this issue,we propose a clustered hierarchical pers...Federated learning faces challenges with non-IID data distributions,often resulting in suboptimal performance for individual clients with the global model.To address this issue,we propose a clustered hierarchical personalized federated learning(CHPFL)framework,which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process.The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning,as edge servers typically offer greater computing power and more efficient communication with the cloud server.Specifically,we use the K-Means++clustering algorithm to group local clients based on their model updates,ensuring that clients with similar data distributions are clustered together and assigned to the same edge server.Each edge server then generates a personalized model by blending the global model with the edge model,which is adaptively updated and optimized through multiple iterations.Additionally,we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance.Experiments on the MNIST,FMNIST,and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL,APFL,and FedALA in non-IID settings.展开更多
基金supported by National Natural Science Foundation of China(Grant No.62071098)Sichuan Science and Technology Program(Grants 2022YFG0319,2023YFG0301 and 2023YFG0018).
文摘With the rapid development of artificial intelligence and Internet of Things technologies,video action recognition technology is widely applied in various scenarios,such as personal life and industrial production.However,while enjoying the convenience brought by this technology,it is crucial to effectively protect the privacy of users’video data.Therefore,this paper proposes a video action recognition method based on personalized federated learning and spatiotemporal features.Under the framework of federated learning,a video action recognition method leveraging spatiotemporal features is designed.For the local spatiotemporal features of the video,a new differential information extraction scheme is proposed to extract differential features with a single RGB frame as the center,and a spatialtemporal module based on local information is designed to improve the effectiveness of local feature extraction;for the global temporal features,a method of extracting action rhythm features using differential technology is proposed,and a timemodule based on global information is designed.Different translational strides are used in the module to obtain bidirectional differential features under different action rhythms.Additionally,to address user data privacy issues,the method divides model parameters into local private parameters and public parameters based on the structure of the video action recognition model.This approach enhancesmodel training performance and ensures the security of video data.The experimental results show that under personalized federated learning conditions,an average accuracy of 97.792%was achieved on the UCF-101 dataset,which is non-independent and identically distributed(non-IID).This research provides technical support for privacy protection in video action recognition.
基金supported in part by the National Natural Science Foundation of China(62472032)the Young Elite Scientists Sponsorship Program by CAST(2023QNRC001)the Fundamental Research Funds for the Central Universities and Research Innovation Project of China University of Political Science and Law(21ZFY52001)。
文摘In federated learning(FL),the distribution of data across different clients leads to the degradation of global model performance in training.Personalized Federated Learning(pFL)can address this problem through global model personalization.Researches over the past few years have calibrated differences in weights across the entire model or optimized only individual layers of the model without considering that different layers of the whole neural network have different utilities,resulting in lagged model convergence and inadequate personalization in non-IID data.In this paper,we propose model layered optimization for feature extractor and classifier(pFedEC),a novel pFL training framework personalized for different layers of the model.Our study divides the model layers into the feature extractor and classifier.We initialize the model's classifiers during model training,while making the local model's feature extractors learn the representation of the global model's feature extractors to correct each client's local training,integrating the utilities of the different layers in the entire model.Our extensive experiments show that pFedEC achieves 92.95%accuracy on CIFAR-10,outperforming existing pFL methods by approximately 1.8%.On CIFAR-100 and Tiny-ImageNet,pFedEC improves the accuracy by at least 4.2%,reaching 73.02%and 28.39%,respectively.
基金Supported by the Scientific and Technological Innovation 2030—Major Project of "New Generation Artificial Intelligence"(2020AAA0109300)。
文摘Federated learning is an emerging distributed privacypreserving framework in which parties are trained collaboratively by sharing model or gradient updates instead of sharing private data. However, the heterogeneity of local data distribution poses a significant challenge. This paper focuses on the label distribution skew, where each party can only access a partial set of the whole class set. It makes global updates drift while aggregating these biased local models. In addition, many studies have shown that deep leakage from gradients endangers the reliability of federated learning. To address these challenges, this paper propose a new personalized federated learning method named MpFedcon. It addresses the data heterogeneity problem and privacy leakage problem from global and local perspectives. Our extensive experimental results demonstrate that MpFedcon yields effective resists on the label leakage problem and better performance on various image classification tasks, robust in partial participation settings, non-iid data,and heterogeneous parties.
基金supported by National Natural Science Foundation of China under Grant No.62202224Natural Science Foundation of Jiangsu Province under Grant No.BK20220882+2 种基金China Postdoctoral Science Foundation under Grant No.2022TQ0154Open Foundation of Ministry Key Laboratory for Safety-Critical Software Development and Verification(Nanjing University of Aeronautics and Astronautics)under Grant No.NJ2024030Dual Innovation Doctor Foundation of Jiangsu Province under Grant No.JSSCBS20220213。
文摘Semantic Communication(SemCom)is a promising paradigm for future 6G networks,where communication performance hinges on the effectiveness of SemCom models,particularly the source-channel encoder and decoder.However,training these models faces significant challenges.Firstly,the privacy-sensitive nature of communication data discourages users from uploading data to centralized servers.Secondly,heterogeneous local data distributions and diverse communication counterparts of different users necessitate personalized SemCom models.Specifically,a user's encoder must align with its receivers'decoders and the transmitted data distribution,while its decoder must adapt to the user's transmitters and received data distribution.To address these challenges,we propose FineFed,a personalized federated learning method with collaborative fine-tuning.Initially,a unified global model is trained distributively via federated learning,eliminating data uploads.Subsequently,users iteratively fine-tune encoders and decoders collaboratively,achieving SemCom model personalization.For encoder fine-tuning,decoders are fixed and shared with transmitters to address distributed loss calculation issues.Each encoder is fine-tuned using the idea of multi-task learning,treating communication with each receiver as a separate task.Then,encoders are fixed.A user shares its decoder with its own transmitters.These transmitters collaboratively fine-tune the user's decoder by the idea of federated multitask learning.Experimental results demonstrate that FineFed improves the average performance of federated SemCom models by 1%-7%,bringing it closer to the performance of centrally-trained models.
文摘Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.
基金supported in part by the National Key R&D Program of China under Grant 2024YFE0200700in part by the National Natural Science Foundation of China under Grant 62201504.
文摘Network architectures assisted by Generative Artificial Intelligence(GAI)are envisioned as foundational elements of sixth-generation(6G)communication system.To deliver ubiquitous intelligent services and meet diverse service requirements,6G network architecture should offer personalized services to various mobile devices.Federated learning(FL)with personalized local training,as a privacypreserving machine learning(ML)approach,can be applied to address these challenges.In this paper,we propose a meta-learning-based personalized FL(PFL)method that improves both communication and computation efficiency by utilizing over-the-air computations.Its“pretraining-and-fine-tuning”principle makes it particularly suitable for enabling edge nodes to access personalized GAI services while preserving local privacy.Experiment results demonstrate the outperformance and efficacy of the proposed algorithm,and notably indicate enhanced communication efficiency without compromising accuracy.
基金supported by the National Natural Science Foundation of China under Grant 61931005Beijing Natural Science Foundation under Grant L202018the Key Laboratory of Internet of Vehicle Technical Innovation and Testing(CAICT),Ministry of Industry and Information Technology under Grant No.KL-2023-001。
文摘In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide efficient and privacypreserving collaborative learning.However,in Io V environment,federated learning faces the challenges introduced by high mobility of vehicles and nonIndependently Identically Distribution(non-IID)of data.High mobility causes FL clients quit and the communication offline.The non-IID data leads to slow and unstable convergence of global model and single global model's weak adaptability to clients with different localization characteristics.Accordingly,this paper proposes a personalized aggregation strategy for hierarchical Federated Learning in Io V environment,including Fed SA(Special Asynchronous Federated Learning with Self-adaptive Aggregation)for low-level FL between a Road Side Unit(RSU)and the vehicles within its coverage,and Fed Att(Federated Learning with Attention Mechanism)for high-level FL between a cloud server and multiple RSUs.Agents self-adaptively obtain model aggregation weight based on Advantage Actor-Critic(A2C)algorithm.Experiments show the proposed strategy encourages vehicles to participate in global aggregation,and outperforms existing methods in training performance.
基金supported by the Science and Technology Project of State Grid Corporation of China(5108-202218280A-2-394-XG)。
文摘Federated learning(FL)is a promising technique to build a power generation model in photovoltaic(PV)scenarios.However,due to the heterogeneity of power generation data,there is a problem of slow convergence of the global model or even deviation from the optimal solution during model training.Therefore,to improve the prediction accuracy and accelerate the model convergence speed,this paper proposes a model functional blocking and differentiated scheduling mechanism under personalized FL framework for intermittent PV power generation.Firstly,cluster analysis is conducted according to longitude,latitude,and altitude to form a model collaborative training region(MCTR).Then,based on the constructed MCTRs,a personalized FL model training method is proposed.This method is based on a combination of global shared convolutional neural network(CNN)model and local personalized long short term memory(LSTM)model,where CNN model block is responsible for feature extraction and LSTM model block is responsible for prediction.It adopts synchronous aggregation for global shared CNN and asynchronous aggregation for personalized LSTM.Furthermore,the FL server performs block scheduling of the CNN-LSTM models and aggregates them based on the regional membership which can provide differentiated and accurate prediction models with different power generation patterns.The simulation results show that the proposed algorithm has the highest accuracy of 85.1%and the best performance on mean absolute error(MAE),root mean square error(RMSE)and mean absolute percentage error(MAPE),with 0.1105,0.1224 and 0.4383 respectively.
基金supported by the National Natural Science Foundation of China under Grant 72331008,and PolyU research project 1-YXBL.
文摘A centralized framework-based data-driven framework for active distribution system state estimation(DSSE)has been widely leveraged.However,it is challenged by potential data privacy breaches due to the aggregation of raw measurement data in a data center.A personalized federated learningbased DSSE method(PFL-DSSE)is proposed in a decentralized training framework for DSSE.Experimental validation confirms that PFL-DSSE can effectively and efficiently maintain data confidentiality and enhance estimation accuracy.
基金supported National Natural Science Foundation of China(No.61976095)Guangdong Province Science and Technology Planning Project,China(No.2018B030323026).
文摘Most finger vein authentication systems suffer from the problem of small sample size.However,the data augmentation can alleviate this problem to a certain extent but did not fundamentally solve the problem of category diversity.So the researchers resort to pre-training or multi-source data joint training methods,but these methods will lead to the problem of user privacy leakage.In view of the above issues,this paper proposes a federated learning-based finger vein authentication framework(FedFV)to solve the problem of small sample size and category diversity while protecting user privacy.Through training under FedFV,each client can share the knowledge learned from its user′s finger vein data with the federated client without causing template leaks.In addition,we further propose an efficient personalized federated aggregation algorithm,named federated weighted proportion reduction(FedWPR),to tackle the problem of non-independent identically distribution caused by client diversity,thus achieving the best performance for each client.To thoroughly evaluate the effectiveness of FedFV,comprehensive experiments are conducted on nine publicly available finger vein datasets.Experimental results show that FedFV can improve the performance of the finger vein authentication system without directly using other client data.To the best of our knowledge,FedFV is the first personalized federated finger vein authentication framework,which has some reference value for subsequent biometric privacy protection research.
基金supported by the Scientific and Technologial Innovation Programs of Higher Education Institutions in Shanxi,China(No.2020L0338)the Shanxi Key Research and Development Program(Nos.202102020101002 and 202102020101005).
文摘Accurate load forecasting is critical for electricity production,transmission,and maintenance.Deep learning(DL)model has replaced other classical models as the most popular prediction models.However,the deep prediction model requires users to provide a large amount of private electricity consumption data,which has potential privacy risks.Edge nodes can federally train a global model through aggregation using federated learning(FL).As a novel distributed machine learning(ML)technique,it only exchanges model parameters without sharing raw data.However,existing forecasting methods based on FL still face challenges from data heterogeneity and privacy disclosure.Accordingly,we propose a user-level load forecasting system based on personalized federated learning(PFL)to address these issues.The obtained personalized model outperforms the global model on local data.Further,we introduce a novel differential privacy(DP)algorithm in the proposed system to provide an additional privacy guarantee.Based on the principle of generative adversarial network(GAN),the algorithm achieves the balance between privacy and prediction accuracy throughout the game.We perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.
基金supported by the National Key R&D Program of China(No.2022YFB2703400).
文摘Federated Learning(FL)is a framework for machine learning on a large-scale distributed dataset,enabling the training of a collaborative model across multiple parties while preserving the privacy of user data.However,in cases where data are distributed in a non-independent and identically distributed(non-iid)manner,the convergence speed of the federated collaborative model and its prediction accuracy on client nodes can be significantly affected.Therefore,personalized FL methods have emerged to further adapt to the data characteristics of different clients.In response to the data heterogeneity issue,this paper presents a multi-task clustering-based personalized federated learning algorithm,which is applied to the prediction of carbon emissions in different regions and enterprises.This algorithm partitions nodes with similar data distributions and aggregates local models within the same cluster to form cluster models.It introduces the concept of multitask learning,dividing the lower layers of cluster models into expert layers.These expert layers of different cluster models are then weighted and aggregated for the acquisition of global knowledge.Additionally,adaptive weight is applied to control the aggregation of expert layers,thereby achieving model personalization at the local level.Simulation experiments conducted on carbon emission prediction data demonstrate that the proposed algorithm performs better in various evaluation metrics compared with the Federated Averaging(FedAvg)algorithm and traditional clustering personalized federated learning algorithm.It also exhibits excellent experimental results and performance when dealing with different quantities of heterogeneous data distributions.
基金supported by the Key Research and Development Program of China(No.2022YFC3005401)the Key Research and Development Program of China,Yunnan Province(No.202203AA080009)+2 种基金the Technology Talent and Platform Program of Yunnan Province(No.202405AK340002)the Technology Project of Huaneng Group(No.HNKJ22-HF92)the High Performance Computing Platform,Hohai University,China.
文摘The growth of sensory data is unlocking a wave of intelligent sensing analysis.Currently,personalized Federated Learning(pFL)methods are used in intelligent sensing analysis but overlook two aspects:(1)global model preference,causing poor global model performance for minority classes on sensing device data,and(2)dynamic role differences in each layer of deep neural network.In light of this,we present a novel pFL framework over edge-cloud collaborative network,named pFL-Sensing,for intelligent sensing analysis.Specifically,the sensing device serves as an edge server.Each edge server produces a customized model through model training and model aggregation phases.In model training,we design a loss function to alleviate the issue of the global model preference.In model aggregation,layer aggregation and an Adaptive Weight Calculation(AWC)mechanism are proposed to capture dynamic role differences of model layers.Experimental results demonstrate the effectiveness of pFL-Sensing in intelligent sensing analysis.
基金Project supported by the National Key R&D Program of China(No.2022ZD0160702)the STCSM(Nos.22511106101,18DZ2270700,and 21DZ1100-100)+1 种基金the 111 Plan(No.BP0719010)the State Key Laboratory of UHD Video and Audio Production and Presentation。
文摘Cross-silo federated learning(FL),which benefits from relatively abundant data and rich computing power,is drawing increasing focus due to the significant transformations that foundation models(FMs)are instigating in the artificial intelligence field.The intensified data heterogeneity issue of this area,unlike that in cross-device FL,is caused mainly by substantial data volumes and distribution shifts across clients,which requires algorithms to comprehensively consider the personalization and generalization balance.In this paper,we aim to address the objective of generalized and personalized federated learning(GPFL)by enhancing the global model’s cross-domain generalization capabilities and simultaneously improving the personalization performance of local training clients.By investigating the fairness of performance distribution within the federation system,we explore a new connection between generalization gap and aggregation weights established in previous studies,culminating in the fairness-guided federated training for generalization and personalization(FFT-GP)approach.FFT-GP integrates a fairness-aware aggregation(FAA)approach to minimize the generalization gap variance among training clients and a meta-learning strategy that aligns local training with the global model’s feature distribution,thereby balancing generalization and personalization.Our extensive experimental results demonstrate FFT-GP’s superior efficacy compared to existing models,showcasing its potential to enhance FL systems across a variety of practical scenarios.
文摘Federated learning faces challenges with non-IID data distributions,often resulting in suboptimal performance for individual clients with the global model.To address this issue,we propose a clustered hierarchical personalized federated learning(CHPFL)framework,which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process.The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning,as edge servers typically offer greater computing power and more efficient communication with the cloud server.Specifically,we use the K-Means++clustering algorithm to group local clients based on their model updates,ensuring that clients with similar data distributions are clustered together and assigned to the same edge server.Each edge server then generates a personalized model by blending the global model with the edge model,which is adaptively updated and optimized through multiple iterations.Additionally,we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance.Experiments on the MNIST,FMNIST,and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL,APFL,and FedALA in non-IID settings.
