Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity MatchingDownload PDF

Published: 31 Oct 2022, Last Modified: 15 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: federated learning
Abstract: In real-world federated learning scenarios, participants could have their own personalized labels incompatible with those from other clients, due to using different label permutations or tackling completely different tasks or domains. However, most existing FL approaches cannot effectively tackle such extremely heterogeneous scenarios since they often assume that (1) all participants use a synchronized set of labels, and (2) they train on the same tasks from the same domain. In this work, to tackle these challenges, we introduce Factorized-FL, which allows to effectively tackle label- and task-heterogeneous federated learning settings by factorizing the model parameters into a pair of rank-1 vectors, where one captures the common knowledge across different labels and tasks and the other captures knowledge specific to the task for each local model. Moreover, based on the distance in the client-specific vector space, Factorized-FL performs a selective aggregation scheme to utilize only the knowledge from the relevant participants for each client. We extensively validate our method on both label- and domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods. The code is available at https://github.com/wyjeong/Factorized-FL.
TL;DR: We study label- and domain-heterogeneity in federated learning scenarios and propose a novel method, Factorized FL, which factorizes model parameters and performs similarity matching with the factorized vectors
Supplementary Material: pdf
16 Replies