Timezone: »

Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching
Wonyong Jeong · Sung Ju Hwang

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #703

In real-world federated learning scenarios, participants could have their own personalized labels which are 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 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.

Author Information

Wonyong Jeong (Korea Advanced Institute of Science and Technology)
Sung Ju Hwang (KAIST, AITRICS)

More from the Same Authors