FedCASKD: A Client-Aware Federated Distillation Framework for Robust Learning Under Heterogeneous Edge Environments
Future Internet · 26.05.2026 · 18 (6) · 285
DOI: 10.3390/fi18060285 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 26.05.2026. Verfasst von Fangfang Shan und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the Key Research and Development Program of Henan Province.
Abstract (Originalsprache)
Federated Learning (FL) enables privacy-preserving model training in edge and IoT environments. However, in adversarial settings, FL suffers from two key challenges: robustness degradation due to data heterogeneity and poisoning attacks, and runtime instability on resource-constrained devices. Existing work mainly focuses on robustness while overlooking system-level stability. To address this, we propose FedCASKD, a robustness- and stability-aware FL framework. It employs a score-based soft aggregation mechanism to suppress unreliable client updates without requiring a trusted dataset, and introduces a selection-aware bidirectional knowledge distillation protocol to mitigate model drift under Non-IID data. The novelty lies in integrating aggregation and distillation into a unified feedback framework that enhances robustness and stability. Experiments on AGNews and SogouNews show that FedCASKD outperforms baselines under label-flipping attacks and heterogeneous settings. Memory and Out-of-Memory (OOM) tests further demonstrate its superior runtime stability in edge environments.
Förderung
- the National Natural Science Foundation of China
- the Key Research and Development Program of Henan Province
Zitieren
APA
Shan, F., Fan, L., Liu, Y., Chen, Z., & Mao, Y. (2026). FedCASKD: A Client-Aware Federated Distillation Framework for Robust Learning Under Heterogeneous Edge Environments. Future Internet, 18(6), 285. https://doi.org/10.3390/fi18060285
Vancouver
Shan F, Fan L, Liu Y, Chen Z, Mao Y. FedCASKD: A Client-Aware Federated Distillation Framework for Robust Learning Under Heterogeneous Edge Environments. Future Internet. 2026;18(6):285. doi:10.3390/fi18060285
BibTeX
@article{Shan2026,
author = {Shan, Fangfang and Fan, Lulu and Liu, Yuhang and Chen, Zhuo and Mao, Yifan},
title = {FedCASKD: A Client-Aware Federated Distillation Framework for Robust Learning Under Heterogeneous Edge Environments},
journal = {Future Internet},
year = {2026},
volume = {18},
number = {6},
pages = {285},
doi = {10.3390/fi18060285}
}
EUVIMED