Papers › An Improved Algorithm for Clustered Federated Learning

An Improved Algorithm for Clustered Federated Learning

20 Oct 2022arXiv:2210.11538archive 2025-07-28

Harshvardhan, Avishek Ghosh, Arya Mazumdar

In this paper, we address the dichotomy between heterogeneous models and simultaneous training in Federated Learning (FL) via a clustering framework. We define a new clustering model for FL based on the (optimal) local models of the users: two users belong to the same cluster if their local models are close; otherwise they belong to different clusters. A standard algorithm for clustered FL is proposed in, called IFCA, which requires suitable initialization and the knowledge of hyper-parameters like the number of clusters (which is often quite difficult to obtain in practical applications) to converge. We propose an improved algorithm, Successive Refine Federated Clustering Algorithm (SR-FCA), which removes such restrictive assumptions. SR-FCA treats each user as a singleton cluster as an initialization, and then successively refine the cluster estimation via exploiting similar users belonging to the same cluster. In any intermediate step, SR-FCA uses a robust federated learning algorithm within each cluster to exploit simultaneous training and to correct clustering errors. Furthermore, SR-FCA does not require any good initialization (warm start), both in theory and practice. We show that with proper choice of learning rate, SR-FCA incurs arbitrarily small clustering error. Additionally, we validate the performance of our algorithm on standard FL datasets in non-convex problems like neural nets, and we show the benefits of SR-FCA over baselines.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

harshv834/sr-fca officialmentioned in paperpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringFederated Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections