paper-with-me

홈 › Papers

A Coalition Formation Game Approach for Personalized Federated Learning

2022-02-05 · Leijie Wu, Song Guo, Yaohong Ding, Yufeng Zhan, Jie Zhang

Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot. Although the state-of-the-art methods with model similarity-based pairwise collaboration have achieved promising performance, they neglect the fact that model aggregation is essentially a collaboration process within the coalition, where the complex multiwise influences take place among clients. In this paper, we first apply Shapley value (SV) from coalition game theory into the PFL scenario. To measure the multiwise collaboration among a group of clients on the personalized learning performance, SV takes their marginal contribution to the final result as a metric. We propose a novel personalized algorithm: pFedSV, which can 1. identify each client's optimal collaborator coalition and 2. perform personalized model aggregation based on SV. Extensive experiments on various datasets (MNIST, Fashion-MNIST, and CIFAR-10) are conducted with different Non-IID data settings (Pathological and Dirichlet). The results show that pFedSV can achieve superior personalized accuracy for each client, compared to the state-of-the-art benchmarks.

📄 PDF Abstract BibTeX arXiv:2202.02502

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityFederated LearningPersonalized Federated Learning

Similar Papers 제목 키워드 기반

Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning

2025-09-28 · Danni Yang, Zhikang Chen, Sen Cui, Mengyue Yang 외 arxiv

Federated continual learning (FCL) has garnered increasing attention for its ability to support distributed computation in environments with evolving data distributions. However, the emergence of new tasks introduces bot…

Continual Learning

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

2024-12-20 · Xiaobing Chen, Xiangwei Zhou, Songyang Zhang, Mingxuan Sun

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…

AttributeFederated Learning

Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approach

2026-07-29 · Cengis Hasan arxiv

Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coaliti…

Federated Learning

Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation

2020-10-02 · Kate Donahue, Jon Kleinberg

Federated learning is a setting where agents, each with access to their own data source, combine models from local data to create a global model. If agents are drawing their data from different distributions, though, fed…

Federated Learning

Design of Two-Level Incentive Mechanisms for Hierarchical Federated Learning

2023-04-09 · Shunfeng Chu, Jun Li, Kang Wei, Yuwen Qian 외

Hierarchical Federated Learning (HFL) is a distributed machine learning paradigm tailored for multi-tiered computation architectures, which supports massive access of devices' models simultaneously. To enable efficient H…

Federated LearningVocal Bursts Valence Prediction