2021
Heterogeneity for the Win: One-Shot Federated Clustering
ICML 2021spotlight
In this work, we explore the unique challenges—and opportunities—of unsupervised federated learning (FL). We develop and analyze a one-shot federated clustering scheme, kfed, based on the widely-used Lloyd’s method for $k$-means clustering. In contrast to many supervised problems, we show that the i…