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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xiaobing, Zhou, Xiangwei, Zhang, Songyang, Sun, Mingxuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915072850264064
author Chen, Xiaobing
Zhou, Xiangwei
Zhang, Songyang
Sun, Mingxuan
author_facet Chen, Xiaobing
Zhou, Xiangwei
Zhang, Songyang
Sun, Mingxuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game
Chen, Xiaobing
Zhou, Xiangwei
Zhang, Songyang
Sun, Mingxuan
Computer Science and Game Theory
Machine Learning
I.2.6; I.2.11
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.
title DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game
topic Computer Science and Game Theory
Machine Learning
I.2.6; I.2.11
url https://arxiv.org/abs/2412.15492