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

TL;DR

DualGFL introduces a dual-level game framework for federated learning, combining coalition formation and auction-based participation to better model participant interactions and improve overall utility.

Contribution

It proposes a novel dual-level game approach with a Pareto-optimal coalition partitioning and multi-attribute auction, capturing complex participant dynamics in federated learning.

Findings

Improves server and client utility in federated learning.

Effectively models complex participant interactions.

Demonstrates superior performance on real-world datasets.

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.