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

arXiv:2403.04144v1 Announce Type: cross
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 …

abstract arxiv challenge client clustering collaborative cs.dc cs.lg data decentralized devices distributed distribution enabling federated learning independent key machine machine learning paradigm samples through training type