A Bayesian Framework for Clustered Federated Learning

2024-10-20 · Peng Wu, Tales Imbiriba, Pau Closas

One of the main challenges of federated learning (FL) is handling non-independent and identically distributed (non-IID) client data, which may occur in practice due to unbalanced datasets and use of different data sources across clients. Knowledge sharing and model personalization are key strategies for addressing this issue. Clustered federated learning is a class of FL methods that groups clients that observe similarly distributed data into clusters, such that every client is typically associated with one data distribution and participates in training a model for that distribution along their cluster peers. In this paper, we present a unified Bayesian framework for clustered FL which associates clients to clusters. Then we propose several practical algorithms to handle the, otherwise growing, data associations in a way that trades off performance and computational complexity. This work provides insights on client-cluster associations and enables client knowledge sharing in new ways. The proposed framework circumvents the need for unique client-cluster associations, which is seen to increase the performance of the resulting models in a variety of experiments.

📄 PDF Abstract BibTeX arXiv:2410.15473

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion

2023-09-20 · Thanveer Shaik, Xiaohui Tao, Lin Li, Niall Higgins 외

Federated Learning (FL) is currently one of the most popular technologies in the field of Artificial Intelligence (AI) due to its collaborative learning and ability to preserve client privacy. However, it faces challenge…

Clustering Federated Learning Representation Learning

Bayesian Federated Model Compression for Communication and Computation Efficiency

2024-04-11 · Chengyu Xia, Danny H. K. Tsang, Vincent K. N. Lau

In this paper, we investigate Bayesian model compression in federated learning (FL) to construct sparse models that can achieve both communication and computation efficiencies. We propose a decentralized Turbo variationa…

Bayesian Inference Federated Learning Model Compression

DPMM-CFL: Clustered Federated Learning via Dirichlet Process Mixture Model Nonparametric Clustering

2025-10-08 · Mariona Jaramillo-Civill, Peng Wu, Pau Closas arxiv

Clustered Federated Learning (CFL) improves performance under non-IID client heterogeneity by clustering clients and training one model per cluster, thereby balancing between a global model and fully personalized models.…

Federated Learning Bayesian Inference

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning

2021-02-25 · Shaoxiong Ji, Yue Tan, Teemu Saravirta, Zhiqin Yang 외

Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. As a flexible learning setting, federated learning has the potential to i…

Federated Learning Meta-Learning reinforcement-learning Reinforcement Learning (RL)+1

Novel clustered federated learning based on local loss

2024-07-12 · Endong Gu, Yongxin Chen, Hao Wen, Xingju Cai 외

This paper proposes LCFL, a novel clustering metric for evaluating clients' data distributions in federated learning. LCFL aligns with federated learning requirements, accurately assessing client-to-client variations in …

Clustering Federated Learning