Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization
IEEE Transactions on Mobile Computing · 2024-12 · 23 (12) · 15196-15209
DOI: 10.1109/tmc.2024.3455331 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-12. Verfasst von Anran Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Nanyang Technological University, RIE2025 Industry Alignment Fund, Industry Collaboration Projects.
Abstract (Originalsprache)
Federated Learning (FL) enables massive local data owners to collaboratively train a deep learning model without disclosing their private data. The importance of local data samples from various data owners to FL models varies widely. This is exacerbated by the presence of noisy data that exhibit large losses similar to important (hard) samples. Currently, there lacks an FL approach that can effectively distinguish hard samples (which are beneficial) from noisy samples (which are harmful). To bridge this gap, we propose the joint Federated Meta-Weighting based Client and Sample Selection (FedMW-CSS) approach to simultaneously mitigate label noise and hard sample selection. It is a bilevel optimization approach for FL client-and-sample selection and global model construction to achieve hard sample-aware noise-robust learning in a privacy preserving manner. It performs meta-learning based online approximation to iteratively update global FL models, select the most positively influential samples and deal with training data noise. To utilize both the instance-level information and class-level information for better performance improvements, FedMW-CSS efficiently learns a class-level weight by manipulating gradients at the class level, e.g., it performs a gradient descent step on class-level weights, which only relies on intermediate gradients. Theoretically, we analyze the privacy guarantees and convergence of FedMW-CSS. Extensive experiments comparison against eight state-of-the-art baselines on six real-world datasets in the presence of data noise and heterogeneity shows that FedMW-CSS achieves up to 28.5% higher test accuracy, while saving communication and computation costs by at least 49.3% and 1.2%, respectively.
Förderung
- Nanyang Technological University
- RIE2025 Industry Alignment Fund
- Industry Collaboration Projects
- Agency for Science, Technology and Research
- Alibaba Group
- National Research Foundation Singapore
- DSO National Laboratories
- AI Singapore Programme AISG
Zitieren
APA
Li, A., Wang, G., Hu, M., Sun, J., Zhang, L., Tuan, L. A., & Yu, H. (2024). Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization. IEEE Transactions on Mobile Computing, 23(12), 15196-15209. https://doi.org/10.1109/tmc.2024.3455331
Vancouver
Li A, Wang G, Hu M, Sun J, Zhang L, Tuan LA, et al. Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization. IEEE Transactions on Mobile Computing. 2024;23(12):15196-15209. doi:10.1109/tmc.2024.3455331
BibTeX
@article{Li2024,
author = {Li, Anran and Wang, Guangjing and Hu, Ming and Sun, Jianfei and Zhang, Lan and Tuan, Luu Anh and Yu, Han},
title = {Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {12},
pages = {15196--15209},
doi = {10.1109/tmc.2024.3455331}
}
EUVIMED