CCFC++: Enhancing Federated Clustering through Feature Decorrelation

arXiv:2402.12852v1 Announce Type: new
Abstract: In federated clustering, multiple data-holding clients collaboratively group data without exchanging raw data. This field has seen notable advancements through its marriage with contrastive learning, exemplified by Cluster-Contrastive Federated Clustering (CCFC). However, CCFC suffers from heterogeneous data across clients, leading to poor and unrobust performance. Our study conducts both empirical and theoretical analyses to understand the impact of heterogeneous data on CCFC. Findings indicate that increased data heterogeneity exacerbates dimensional collapse in CCFC, evidenced by …

abstract arxiv cluster clustering cs.lg data feature marriage multiple performance raw study through type