PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 6, 20240 citationsOpen Access

FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering

View Full Paper
MIMd. Sirajul IslamSJSimin JavaherianFXFei Xu

Key Points

Key points are not available for this paper at this time.

Abstract

Federated learning (FL) is an emerging distributed machine learning paradigm enabling collaborative model training on decentralized devices without exposing their local data. A key challenge in FL is the uneven data distribution across client devices, violating the well-known assumption of independent-and-identically-distributed (IID) training samples in conventional machine learning. Clustered federated learning (CFL) addresses this challenge by grouping clients based on the similarity of their data distributions. However, existing CFL approaches require a large number of communication rounds for stable cluster formation and rely on a predefined number of clusters, thus limiting their flexibility and adaptability. This paper proposes FedClust, a novel CFL approach leveraging correlations between local model weights and client data distributions. FedClust groups clients into clusters in a one-shot manner using strategically selected partial model weights and dynamically accommodates newcomers in real-time. Experimental results demonstrate FedClust outperforms baseline approaches in terms of accuracy and communication costs.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Islam et al. (2024) studied this question.

synapsesocial.com/papers/68e758b6b6db6435876d0143https://doi.org/10.48550/arxiv.2403.04144
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering2024
  2. 2FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering2024 · 16 citations
  3. 3Clustered Federated Learning with Adaptive Similarity for Non-IID Data2025
  4. 4Dynamic Client Clustering, Bandwidth Allocation, and Workload Optimization for Semi-synchronous Federated Learning2024
  5. 5FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data2024 · 6 citations