The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,pri...The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,privacy-preserving distributed learning frameworks,represented by swarm learning and federated learning,have been investigated recently with the sensitive healthcare data retaining in its local premises.However,existing frameworks use a one-size-fits-all mode that tunes one model for all healthcare situations,which could hardly fit the usually diverse disease prediction in practice.This work introduces the idea of ensemble learning into privacypreserving distributed learning and presents the En-split framework,where the predictions of multiple expert models with specialized diagnostic capabilities are jointly explored.Considering the exacerbation of communication and computation burdens with multiple models during learning,model split is used to partition targeted models into two parts,with hospitals focusing on building the feature-enriched shallow layers.Meanwhile,dedicated noises are implemented to the edge layers for differential privacy protection.Experiments on two public datasets demonstrate En-split’s superior performance on accuracy and efficiency,compared with existing distributed learning frameworks.展开更多
Federated multi-task learning(FMTL)has emerged as a promising framework for learning multiple tasks simultaneously with client-aware personalized models.While the majority of studies have focused on dealing with the n...Federated multi-task learning(FMTL)has emerged as a promising framework for learning multiple tasks simultaneously with client-aware personalized models.While the majority of studies have focused on dealing with the non-independent and identically distributed(Non-IID)characteristics of client datasets,the issue of task heterogeneity has largely been overlooked.Dealing with task heterogeneity often requires complex models,making it impractical for federated learning in resource-constrained environments.In addition,the varying nature of these heterogeneous tasks introduces inductive biases,leading to interference during aggregation and potentially resulting in biased global models.To address these issues,we propose a hierarchical FMTL framework,referred to as FedBone,to facilitate the construction of large-scale models with improved generalization.FedBone leverages server-client split learning and gradient projection to split the entire model into two components:1)a large-scale general model(referred to as the general model)on the cloud server,and 2)multiple task-specific models(referred to as client models)on edge clients,accommodating devices with limited compute power.To enhance the robustness of the large-scale general model,we incorporate the conflicting gradient projection technique into FedBone to rectify the skewed gradient direction caused by aggregating gradients from heterogeneous tasks.The proposed FedBone framework is evaluated on three benchmark datasets and one real ophthalmic dataset.The comprehensive experiments demonstrate that FedBone efficiently adapts to the heterogeneous local tasks of each client and outperforms existing federated learning algorithms in various dense prediction and classification tasks while utilizing off-the-shelf computational resources on the client side.展开更多
基金supported by the National Natural Science Foundation of China(62172155)the NationalKey Research andDevelopment Programof China(2022YFF1203001)+2 种基金the Science and Technology Innovation Program of Hunan Province(Nos.2022RC3061,2023RC3027)the Graduate Research Innovation Project of Hunan Province(XJCX2023157)NUDT Scientific Project“Research on Privacy-Enhancing Computing Technologies for Activity Trajectory Data”.
文摘The isolation of healthcare data among worldwide hospitals and institutes forms barriers for fully realizing the data-hungry artificial intelligence(AI)models promises in renewing medical services.To overcome this,privacy-preserving distributed learning frameworks,represented by swarm learning and federated learning,have been investigated recently with the sensitive healthcare data retaining in its local premises.However,existing frameworks use a one-size-fits-all mode that tunes one model for all healthcare situations,which could hardly fit the usually diverse disease prediction in practice.This work introduces the idea of ensemble learning into privacypreserving distributed learning and presents the En-split framework,where the predictions of multiple expert models with specialized diagnostic capabilities are jointly explored.Considering the exacerbation of communication and computation burdens with multiple models during learning,model split is used to partition targeted models into two parts,with hospitals focusing on building the feature-enriched shallow layers.Meanwhile,dedicated noises are implemented to the edge layers for differential privacy protection.Experiments on two public datasets demonstrate En-split’s superior performance on accuracy and efficiency,compared with existing distributed learning frameworks.
基金supported by the Beijing Municipal Science and Technology Commission under Grant No.Z221100002722009the National Natural Science Foundation of China under Grant No.62202455+1 种基金the Youth Innovation Promotion Association of Chinese Academy of Sciences(CAS),the Hunan Provincial Natural Science Foundation of China under Grant No.2023JJ70034the Science Research Foundation of the CAS-Aier Joint Laboratory on Digital Ophthalmology under Grant No.SZYK202201.
文摘Federated multi-task learning(FMTL)has emerged as a promising framework for learning multiple tasks simultaneously with client-aware personalized models.While the majority of studies have focused on dealing with the non-independent and identically distributed(Non-IID)characteristics of client datasets,the issue of task heterogeneity has largely been overlooked.Dealing with task heterogeneity often requires complex models,making it impractical for federated learning in resource-constrained environments.In addition,the varying nature of these heterogeneous tasks introduces inductive biases,leading to interference during aggregation and potentially resulting in biased global models.To address these issues,we propose a hierarchical FMTL framework,referred to as FedBone,to facilitate the construction of large-scale models with improved generalization.FedBone leverages server-client split learning and gradient projection to split the entire model into two components:1)a large-scale general model(referred to as the general model)on the cloud server,and 2)multiple task-specific models(referred to as client models)on edge clients,accommodating devices with limited compute power.To enhance the robustness of the large-scale general model,we incorporate the conflicting gradient projection technique into FedBone to rectify the skewed gradient direction caused by aggregating gradients from heterogeneous tasks.The proposed FedBone framework is evaluated on three benchmark datasets and one real ophthalmic dataset.The comprehensive experiments demonstrate that FedBone efficiently adapts to the heterogeneous local tasks of each client and outperforms existing federated learning algorithms in various dense prediction and classification tasks while utilizing off-the-shelf computational resources on the client side.
