Overcoming Noisy Labels and Non-IID Data in Edge Federated Learning
IEEE Transactions on Mobile Computing · 2024-12 · 23 (12) · 11406-11421
DOI: 10.1109/tmc.2024.3398801 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-12. Verfasst von Yang Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangsu Province Science Foundation for Youths, USTC Research Funds of the Double First-Class Initiative.
Abstract (Originalsprache)
Federated learning (FL) enables edge devices to cooperatively train models without exposing their raw data. However, implementing a practical FL system at the network edge mainly faces three challenges: label noise, data non-IIDness, and device heterogeneity, which seriously harm model performance and slow down convergence speed. Unfortunately, none of the existing works tackle all three challenges simultaneously. To this end, we develop a novel FL system, called Aorta, which features adaptive dataset construction and aggregation weight assignment. On each client, Aorta first calibrates potentially noisy labels and then constructs a training dataset with low noise, balanced distribution, and proper size. To fully utilize limited data on clients, we propose a global model guided method to select clean data and progressively correct noisy labels. To achieve balanced class distribution and proper dataset size, we propose a distribution-and-capability-aware data augmentation method to generate local training data. On the server, Aorta assigns aggregation weights based on the quality of local models to ensure that high-quality models have a greater influence on the global model. The model quality is measured through its cosine similarity with a benchmark model, which is trained on a clean and balanced dataset. We conduct extensive experiments on four datasets with various settings, including different noise types/ratios and non-IID types/levels. Compared to the baselines, Aorta improves model accuracy up to 9.8% on the datasets with moderate noise and non-IIDness, while providing a speedup of 4.2× on average when achieving the same target accuracy.
Förderung
- National Natural Science Foundation of China
- Jiangsu Province Science Foundation for Youths
- USTC Research Funds of the Double First-Class Initiative
Zitieren
APA
Xu, Y., Liao, Y., Wang, L., Xu, H., Jiang, Z., & Zhang, W. (2024). Overcoming Noisy Labels and Non-IID Data in Edge Federated Learning. IEEE Transactions on Mobile Computing, 23(12), 11406-11421. https://doi.org/10.1109/tmc.2024.3398801
Vancouver
Xu Y, Liao Y, Wang L, Xu H, Jiang Z, Zhang W. Overcoming Noisy Labels and Non-IID Data in Edge Federated Learning. IEEE Transactions on Mobile Computing. 2024;23(12):11406-11421. doi:10.1109/tmc.2024.3398801
BibTeX
@article{Xu2024,
author = {Xu, Yang and Liao, Yunming and Wang, Lun and Xu, Hongli and Jiang, Zhida and Zhang, Wuyang},
title = {Overcoming Noisy Labels and Non-IID Data in Edge Federated Learning},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {12},
pages = {11406--11421},
doi = {10.1109/tmc.2024.3398801}
}
EUVIMED