FedL2P: Federated Learning to Personalize

Royson Lee, Minyoung Kim, Da Li, Xinchi Qiu, Timothy Hospedales, Ferenc Huszar, Nicholas D. Lane

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those common models to the specifics of each client's local data distribution. However, different FL problems may require different personalization strategies, and it may not even be possible to define an effective one-size-fits-all personalization strategy for all clients: depending on how similar each client's optimal predictor is to that of the global model, different personalization strategies may be preferred. In this paper, we consider the federated meta-learning problem of learning personalization strategies. Specifically, we consider meta-nets that induce the batch-norm and learning rate parameters for each client given local data statistics. By learning these meta-nets through FL, we allow the whole FL network to collaborate in learning a customized personalization strategy for each client. Empirical results show that this framework improves on a range of standard hand-crafted personalization baselines in both label and feature shift situations.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 36 (NeurIPS 2023)
PublisherCurran Associates Inc
Pages14818-14836
Number of pages19
Volume36
Publication statusAccepted/In press - 21 Sept 2023
EventThirty-seventh Conference on Neural Information Processing Systems - New Orleans, United States
Duration: 10 Dec 202316 Dec 2023
Conference number: 37
https://nips.cc/

Conference

ConferenceThirty-seventh Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2023
Country/TerritoryUnited States
CityNew Orleans
Period10/12/2316/12/23
Internet address

Fingerprint

Dive into the research topics of 'FedL2P: Federated Learning to Personalize'. Together they form a unique fingerprint.

Cite this