Abstract
Federated learning (FL) opens a new promising paradigm for the Industrial Internet of Things (IoT) since it can collaboratively train machine learning models without sharing private data. However, deploying FL frameworks in real IoT scenarios faces three critical challenges, i.e., statistical heterogeneity, resource constraint, and fairness. To address these challenges, we design a fair and efficient FL method, termed FedASA, which can address the challenge of statistical heterogeneity in resource-constrained scenarios by determining the shared architecture adaptively. In FedASA, we first present a cell-wised shared architecture selection strategy, which can adaptively construct the shared architecture for each device. We then design a cell-based aggregation algorithm for aggregating heterogeneous shared architectures. In addition, we provide a theoretical analysis of the federated error bound, which provides a theoretical guarantee for the fairness. At the same time, we prove the convergence of FedASA at the first-order stationary point. We evaluate the performance of FedASA through extensive simulation and experiments. Experimental results in cross-location scenarios show that FedASA outperformed the state-of-the-art approaches, improving accuracy by up to 13.27% with better fairness and faster convergence and communication requirement has been reduced by 81.49%.
Funding Information
  • National Natural Science Foundation of China (62172003, 92167204, 62072030, 62302539)
  • University Synergy Innovation Program of Anhui Province (GXXT-2022-051)
  • Open Fund of Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet (IASII24-01)
  • China Postdoctoral Science Foundation (2024T170047, GZC20230223, 2024M750165)
  • National Research Foundation Singapore
  • Info-communications Media Development Authority
  • Future Communications Research & Development Programme, Defence Science Organisation (DSO) National Laboratories under the AI Singapore Programme (FCP-NTU RG-2022-010, FCP-ASTAR-TG-2022-003)
  • Ministry of Education - Singapore (RG87/22)
  • NTU Centre for Computational Technologies in Finance

This publication has 36 references indexed in Scilit: