文献类型：期刊文献

英文题名：IDFL: Incentive-driven federated learning with selfish clients

作者：Xu, Jin[1];Zhang, Hengrun[1];Yu, Huiqun[1];Fan, Guisheng[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2026

卷号：131

外文期刊名：INFORMATION FUSION

收录：;EI(收录号：20260520005196);WOS:【SCI-EXPANDED(收录号:WOS:001679959400001)】；

基金：This work was partially supported by the NSF of China under grants No. 62372174 and No. 62276097, Shanghai Municipal Special Fund for Promoting High Quality Development (No. 2021-GYHLW-01007) , the Shanghai 2024 Science and Technology Innovation Action Plan Star Cultivation (Sailing Program, No. 24YF2720000) , and the Science Foundation of Shanghai Key Laboratory of Computer Software Evaluating and Testing under Grant SSTL2024_02.

语种：英文

外文关键词：Federated learning; Batch size optimization; Convergence-generalization tradeoff; Stackelberg game; Trust management

摘要：Heterogeneity challenges have been long discussed in Federated Learning (FL). Among these challenges, statistical heterogeneity, where non-independent and identical (non-IID) data distributions across clients severely impact model convergence and performance, remains particularly problematic. While existing batch size optimization strategies effectively address system-level heterogeneity and resource constraints, they inadequately tackle statistical heterogeneity, often simply increasing batch sizes without theoretical justification. Such approaches overlook a critical convergence-generalization dilemma well-established in traditional machine learning: larger batch sizes accelerate convergence but may deteriorate generalization performance beyond critical thresholds, which is usually termed "generalization gap". To bridge this gap in FL, we propose a comprehensive framework with three key contributions. First, we establish a batch size optimization mechanism that balances convergence and generalization objectives through a penalty function, providing mathematically derived closed-form solutions for optimal batch sizes. Second, we design a Stackelberg game-based incentive mechanism that coordinates batch size assignments with resource contributions while ensuring fair reward allocation to maximize individual client utility (defined as the difference between rewards and costs). Third, we develop a two-step verification strategy that detects and mitigates free-riding behaviors while monitoring convergence patterns to terminate ineffective training processes. Extensive experiments on real-world datasets validate our approach, demonstrating significant improvements in both convergence performance and fairness compared to state-of-the-art algorithms. Ablation studies confirm the effectiveness of each component.