Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

TL;DR

This paper introduces Clustered Federated Learning (CFL), a novel framework that groups clients based on data distribution similarities to improve model performance in federated settings, especially with non-i.i.d. data.

Contribution

CFL is a model-agnostic, privacy-preserving clustering method that enhances federated learning by exploiting loss surface geometry without altering communication protocols.

Findings

CFL improves model accuracy over standard FL in non-i.i.d. scenarios.

Theoretical guarantees on clustering quality are provided.

Experimental results on neural networks validate CFL's effectiveness.

Abstract

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results if the local clients' data distributions diverge. To address this issue, we present Clustered Federated Learning (CFL), a novel Federated Multi-Task Learning (FMTL) framework, which exploits geometric properties of the FL loss surface, to group the client population into clusters with jointly trainable data distributions. In contrast to existing FMTL approaches, CFL does not require any modifications to the FL communication protocol to be made, is applicable to general non-convex objectives (in particular deep neural networks) and comes with strong mathematical guarantees on the clustering quality. CFL is flexible enough to handle client populations that vary over time and can be implemented in a privacy preserving way. As clustering is only performed after Federated Learning has converged to a stationary point, CFL can be viewed as a post-processing method that will always achieve greater or equal performance than conventional FL by allowing clients to arrive at more specialized models. We verify our theoretical analysis in experiments with deep convolutional and recurrent neural networks on commonly used Federated Learning datasets.