A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments

Siyuan Wu (Nanjing University) · Yongzhe Jia (Nanjing University) · Haolong Xiang (Nanjing University of Information Science and Technology) · Xiaolong Xu (Nanjing University of Information Science and Technology) · Xuyun Zhang (Macquarie University) · Lianyong Qi (China University of Petroleum) · Wanchun Dou (nanjing university)
accuracy and fairness.client participationclient participation patternscritical local parametersdual-end aligned ensemble learningfederated learningheterogeneous clientsimportance-driven selective parameter updateknowledge alignmentlightweight fl platformlocal ensemble learningmodel-heterogeneousperformance fairnessstate-of-the-art performanceupdate conflicts

Federated learning (FL) is a distributed machine learning paradigm that enables multiple clients to collaboratively train a shared model without exposing their raw data. However, existing FL research has primarily focused on optimizing learning performance based on the assumption of uniform client participation, with few studies delving into performance fairness under inconsistent client participation, particularly in model-heterogeneous FL environments. In view of this challenge, we propose PHP-FL, a novel model-heterogeneous FL method that explicitly addresses scenarios with varying client participation probabilities to enhance both model accuracy and performance fairness. Specifically, we introduce a Dual-End Aligned ensemble Learning (DEAL) module, where small auxiliary models on clients are used for dual-end knowledge alignment and local ensemble learning, effectively tackling model heterogeneity without a public dataset. Furthermore, to mitigate update conflicts caused by inconsistent participation probabilities, we propose an Importance-driven Selective Parameter Update (ISPU) module, which accurately updates critical local parameters based on training progress. Finally, we implement PHP-FL on a lightweight FL platform with heterogeneous clients across three different client participation patterns. Extensive experiments under heterogeneous settings and diverse client participation patterns demonstrate that PHP-FL achieves state-of-the-art performance in both accuracy and fairness. Our code is available at: https://github.com/Siyuan01/PHP-FL-main.