ActPerFL: Active Personalized Federated Learning

Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang

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

1 Scopus citations

Abstract

In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients' training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. Consequently, ActPerFL can adapt to the underlying clients' heterogeneity with uncertainty-driven local training and model aggregation. With experimental studies on Sent140 and Amazon Alexa audio data, we show that ActPerFL can achieve superior personalization performance compared with the existing counterparts.

Original languageEnglish (US)
Title of host publicationFL4NLP 2022 - 1st Workshop on Federated Learning for Natural Language Processing, Proceedings of the Workshop
EditorsBill Yuchen Lin, Chaoyang He, Chulin Xie, Fatemehsadat Mireshghallah, Ninareh Mehrabi, Tian Li, Mahdi Soltanolkotabi, Xiang Ren
PublisherAssociation for Computational Linguistics (ACL)
Pages1-5
Number of pages5
ISBN (Electronic)9781955917377
StatePublished - 2022
Event1st Workshop on Federated Learning for Natural Language Processing, FL4NLP 2022 - Dublin, Ireland
Duration: May 27 2022 → …

Publication series

NameFL4NLP 2022 - 1st Workshop on Federated Learning for Natural Language Processing, Proceedings of the Workshop

Conference

Conference1st Workshop on Federated Learning for Natural Language Processing, FL4NLP 2022
Country/TerritoryIreland
CityDublin
Period5/27/22 → …

Bibliographical note

Publisher Copyright:
© 2022 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'ActPerFL: Active Personalized Federated Learning'. Together they form a unique fingerprint.

Cite this