Personalized Cross-Silo Federated Learning on Non-IID Data
Yutao Huang, Lingyang Chu, Zirui Zhou, Lanjun Wang, Jiangchuan Liu, Jian Pei, Yong Zhang
Abstract
Non-IID data present a tough challenge for federated learning. In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. We propose FedAMP, a new method employing federated attentive message passing to facilitate similar clients to collaborate more. We establish the convergence of FedAMP for both convex and non-convex models, and propose a heuristic method to further improve the performance of FedAMP when clients adopt deep neural networks as personalized models. Our extensive experiments on benchmark data sets demonstrate the superior performance of the proposed methods.
Topics & Concepts
Computer scienceBenchmark (surveying)HeuristicPairwise comparisonConvergence (economics)Federated learningDeep learningMachine learningArtificial intelligenceArtificial neural networkData miningEconomicsEconomic growthGeodesyGeographyPrivacy-Preserving Technologies in DataAdvanced Graph Neural NetworksStochastic Gradient Optimization Techniques