Find Your Friends: Personalized Federated Learning with the Right CollaboratorsDownload PDF

Published: 21 Oct 2022, Last Modified: 05 May 2023FL-NeurIPS 2022 PosterReaders: Everyone
Keywords: Federated learning, Personalized federated learning, Decentralized federated learning
TL;DR: We propose a novel personalized decentralized federated learning framework for heterogeneous client data by collaborating with the right clients.
Abstract: In the traditional federated learning setting, a central server coordinates a network of clients to train one global model. However, the global model may serve many clients poorly due to data heterogeneity. Moreover, there may not exist a trusted central party that can coordinate the clients to ensure that each of them can benefit from others. To address these concerns, we present a novel decentralized framework, FedeRiCo, where each client can learn as much or as little from other clients as is optimal for its local data distribution. Based on expectation-maximization, FedeRiCo estimates the utilities of other participants’ models on each client’s data so that everyone can select the right collaborators for learning. As a result, our algorithm outperforms other federated, personalized, and/or decentralized approaches on several benchmark datasets, being the only approach that consistently performs better than training with local data only.
Is Student: No
3 Replies