Federated Local Compact Representation Communication:Framework and Application  

作　　者：Zhengquan Luo Yunlong Wang Zilei Wang 

机构地区：[1]University of Science and Technology of China(USTC),Hefei,230026,China [2]New Laboratory of Pattern Recognition(NLPR),Institute of Automation,Chinese Academy of Sciences,Beijing,100190,China [3]State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS),Institute of Automation,Chinese Academy of Sciences,Beijing,100190,China

出　　处：《Machine Intelligence Research》2024年第6期1103-1120,共18页机器智能研究（英文版）

基　　金：National Natural Science Foundation of China(Nos.62176246,61836008,62006225,61906199 and 62071468);Strategic Priority Research Program of Chinese Academy of Sciences(CAS),China(No.XDA27040700);Beijing Nova Program,China(Nos.Z201100006820050 and Z211100002121010).

摘　　要：The core of federated learning(FL)is to transfer data diversity and distribution knowledge of cross-client domains.Al-though adopted by most FL methods,model-sharing-based communication has limitations such as unstable optimization and lack of reasonable explanation.In this paper,we propose an innovative approach that exploits a highly abstract local compact representation(LCR)as a communication carrier,paving a new feasible path for FL.LCR is not only more intuitive for multiclient joint training but also insensitive to local privacy,particularly in computer vision tasks.The proposed LCR communication-based FL framework aims to improve performance,mitigate negative transfer,and enhance optimization stability.First,based on the domain adaptation theorem,in-depth theoretical proofs guarantee the contribution of representation communication from other domains,which may lead to a tight-er generalization error bound of the local domain.Second,inspired by metric learning,a federated version of the triplet(FedTriplet)loss and distribution similarity reweighting aggregation are proposed to fully digest LCR from other clients and realize the LCRC-based FL framework with better explanations.Cross-client FedTriplet transferring redresses the category boundaries in local latent space,resist-ing overfitting.The modified Wasserstein distance is employed for reweighting aggregation to overcome the negative transfer problem caused by non-i.i.d.factors.Finally,extensive experiments on MNIST/EMNIST and successful iris recognition applications demon-strate that the proposed LCRC framework is superior in terms of accuracy compared to mainstream model-sharing-based FL methods.The visualization results also show significant improvements in the distinguishability of the representation distribution.

关 键 词：Federated learning representation learning domain adaptation BIOMETRICS iris recognition 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]