Collaborative Neural Architecture Search for Personalized Federated Learning
IEEE Transactions on Computers · 2025-01 · 74 (1) · 250-262
DOI: 10.1109/tc.2024.3477945 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2025-01. Verfasst von Yi Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Key-Area Research and Development Program of Guangdong Province, Hong Kong RGC Research Impact Fund, Areas of Excellence Scheme.
Abstract (Originalsprache)
Personalized federated learning (pFL) is a promising approach to train customized models for multiple clients over heterogeneous data distributions. However, existing works on pFL often rely on the optimization of model parameters and ignore the personalization demand on neural network architecture, which can greatly affect the model performance in practice. Therefore, generating personalized models with different neural architectures for different clients is a key issue in implementing pFL in a heterogeneous environment. Motivated by Neural Architecture Search (NAS), a model architecture searching methodology, this paper aims to automate the model design in a collaborative manner while achieving good training performance for each client. Specifically, we reconstruct the centralized searching of NAS into the distributed scheme called Personalized Architecture Search (PAS), where differentiable architecture fine-tuning is achieved via gradient-descent optimization, thus making each client obtain the most appropriate model. Furthermore, to aggregate knowledge from heterogeneous neural architectures, a knowledge distillation-based training framework is proposed to achieve a good trade-off between generalization and personalization in federated learning. Extensive experiments demonstrate that our architecture-level personalization method achieves higher accuracy under the non-iid settings, while not aggravating model complexity over state-of-the-art benchmarks.
Förderung
- Key-Area Research and Development Program of Guangdong Province
- Hong Kong RGC Research Impact Fund
- Areas of Excellence Scheme
- General Research
- Collaborative Research Fund
- Hong Kong Generative AI Research and Development Center from InnoHK
Zitieren
APA
Liu, Y., Guo, S., Zhang, J., Hong, Z., Zhan, Y., & Zhou, Q. (2025). Collaborative Neural Architecture Search for Personalized Federated Learning. IEEE Transactions on Computers, 74(1), 250-262. https://doi.org/10.1109/tc.2024.3477945
Vancouver
Liu Y, Guo S, Zhang J, Hong Z, Zhan Y, Zhou Q. Collaborative Neural Architecture Search for Personalized Federated Learning. IEEE Transactions on Computers. 2025;74(1):250-262. doi:10.1109/tc.2024.3477945
BibTeX
@article{Liu2025,
author = {Liu, Yi and Guo, Song and Zhang, Jie and Hong, Zicong and Zhan, Yufeng and Zhou, Qihua},
title = {Collaborative Neural Architecture Search for Personalized Federated Learning},
journal = {IEEE Transactions on Computers},
year = {2025},
volume = {74},
number = {1},
pages = {250--262},
doi = {10.1109/tc.2024.3477945}
}
EUVIMED