English

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

Computer Science and Game Theory 2024-12-23 v1 Machine Learning

Abstract

Despite some promising results in federated learning using game-theoretical methods, most existing studies mainly employ a one-level game in either a cooperative or competitive environment, failing to capture the complex dynamics among participants in practice. To address this issue, we propose DualGFL, a novel Federated Learning framework with a Dual-level Game in cooperative-competitive environments. DualGFL includes a lower-level hedonic game where clients form coalitions and an upper-level multi-attribute auction game where coalitions bid for training participation. At the lower-level DualGFL, we introduce a new auction-aware utility function and propose a Pareto-optimal partitioning algorithm to find a Pareto-optimal partition based on clients' preference profiles. At the upper-level DualGFL, we formulate a multi-attribute auction game with resource constraints and derive equilibrium bids to maximize coalitions' winning probabilities and profits. A greedy algorithm is proposed to maximize the utility of the central server. Extensive experiments on real-world datasets demonstrate DualGFL's effectiveness in improving both server utility and client utility.

Keywords

Cite

@article{arxiv.2412.15492,
  title  = {DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game},
  author = {Xiaobing Chen and Xiangwei Zhou and Songyang Zhang and Mingxuan Sun},
  journal= {arXiv preprint arXiv:2412.15492},
  year   = {2024}
}

Comments

12 pages, 6 figures. Accepted by AAAI25