Robust Asymmetric Heterogeneous Federated Learning With Corrupted Clients
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2693-2705
DOI: 10.1109/tpami.2025.3527137 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Xiuwen Fang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper studies a challenging robust federated learning task with model heterogeneous and data corrupted clients, where the clients have different local model structures. Data corruption is unavoidable due to factors, such as random noise, compression artifacts, or environmental conditions in real-world deployment, drastically crippling the entire federated system. To address these issues, this paper introduces a novel Robust Asymmetric Heterogeneous Federated Learning (RAHFL) framework. We propose a Diversity-enhanced supervised Contrastive Learning technique to enhance the resilience and adaptability of local models on various data corruption patterns. Its basic idea is to utilize complex augmented samples obtained by the mixed-data augmentation strategy for supervised contrastive learning, thereby enhancing the ability of the model to learn robust and diverse feature representations. Furthermore, we design an Asymmetric Heterogeneous Federated Learning strategy to resist corrupt feedback from external clients. The strategy allows clients to perform selective one-way learning during collaborative learning phase, enabling clients to refrain from incorporating lower-quality information from less robust or underperforming collaborators. Extensive experimental results demonstrate the effectiveness and robustness of our approach in diverse, challenging federated learning environments.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Fang, X., Ye, M., & Du, B. (2025). Robust Asymmetric Heterogeneous Federated Learning With Corrupted Clients. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2693-2705. https://doi.org/10.1109/tpami.2025.3527137
Vancouver
Fang X, Ye M, Du B. Robust Asymmetric Heterogeneous Federated Learning With Corrupted Clients. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2693-2705. doi:10.1109/tpami.2025.3527137
BibTeX
@article{Fang2025,
author = {Fang, Xiuwen and Ye, Mang and Du, Bo},
title = {Robust Asymmetric Heterogeneous Federated Learning With Corrupted Clients},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {4},
pages = {2693--2705},
doi = {10.1109/tpami.2025.3527137}
}
EUVIMED