Litcius/Paper detail

Distribution-Regularized Federated Learning on Non-IID Data

Yansheng Wang, Yongxin Tong, Zimu Zhou, Ruisheng Zhang, Sinno Jialin Pan, Lixin Fan, Qiang Yang

202322 citationsDOI

Abstract

Federated learning (FL) has emerged as a popular machine learning paradigm recently. Compared with traditional distributed learning, its unique challenges mainly lie in communication efficiency and non-IID (heterogeneous data) problem. While the widely adopted framework FedAvg can reduce communication overhead significantly, its effectiveness on non-IID data still lacks exploration. In this paper, we study the non-IID problem of FL from the perspective of domain adaptation. We propose a distribution regularization for FL on non-IID data such that the discrepancy of data distributions between clients is reduced. To further reduce the communication cost, we devise two novel distributed learning algorithms, namely rFedAvg and rFedAvg+, for efficiently learning with the distribution regularization. More importantly, we theoretically establish their convergence for strongly convex objectives. Extensive experiments on 4 datasets with both CNN and LSTM as learning models verify the effectiveness and efficiency of the proposed algorithms.

Topics & Concepts

Computer scienceRegularization (linguistics)Artificial intelligenceOverhead (engineering)Domain adaptationMachine learningConvergence (economics)Transfer of learningData modelingLabeled dataDatabaseEconomic growthEconomicsClassifier (UML)Operating systemPrivacy-Preserving Technologies in DataStochastic Gradient Optimization TechniquesDomain Adaptation and Few-Shot Learning