Personalized Federated Learning on Non-IID Data via Group-based Meta-learning
ACM Transactions on Knowledge Discovery from Data · 31.08.2023 · 17 (4) · 1-20
DOI: 10.1145/3558005 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 22.03.2023. Verfasst von Lei Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 132-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Hong Kong RGC General Research Fund.
Abstract (Originalsprache)
Personalized federated learning (PFL) has emerged as a paradigm to provide a personalized model that can fit the local data distribution of each client. One natural choice for PFL is to leverage the fast adaptation capability of meta-learning, where it first obtains a single global model, and each client achieves a personalized model by fine-tuning the global one with its local data. However, existing meta-learning-based approaches implicitly assume that the data distribution among different clients is similar, which may not be applicable due to the property of data heterogeneity in federated learning. In this work, we propose a Group-based Federated Meta-Learning framework, called G-FML , which adaptively divides the clients into groups based on the similarity of their data distribution, and the personalized models are obtained with meta-learning within each group. In particular, we develop a simple yet effective grouping mechanism to adaptively partition the clients into multiple groups. Our mechanism ensures that each group is formed by the clients with similar data distribution such that the group-wise meta-model can achieve “personalization” at large. By doing so, our framework can be generalized to a highly heterogeneous environment. We evaluate the effectiveness of our proposed G-FML framework on three heterogeneous benchmarking datasets. The experimental results show that our framework improves the model accuracy by up to 13.15% relative to the state-of-the-art federated meta-learning.
Förderung
- National Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research Foundation
- Hong Kong RGC General Research Fund
- Hong Kong RGC Research Impact Fund
- Hong Kong RGC Theme-based Research Scheme
Zitieren
APA
Yang, L., Huang, J., Lin, W., & Cao, J. (2023). Personalized Federated Learning on Non-IID Data via Group-based Meta-learning. ACM Transactions on Knowledge Discovery from Data, 17(4), 1-20. https://doi.org/10.1145/3558005
Vancouver
Yang L, Huang J, Lin W, Cao J. Personalized Federated Learning on Non-IID Data via Group-based Meta-learning. ACM Transactions on Knowledge Discovery from Data. 2023;17(4):1-20. doi:10.1145/3558005
BibTeX
@article{Yang2023,
author = {Yang, Lei and Huang, Jiaming and Lin, Wanyu and Cao, Jiannong},
title = {Personalized Federated Learning on Non-IID Data via Group-based Meta-learning},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2023},
volume = {17},
number = {4},
pages = {1--20},
doi = {10.1145/3558005}
}
EUVIMED