Open access
2026
Federated Learning With Noisy and Imbalanced Data: A Contrastive Reliability-Based Framework for Long-Tail-Aware Client Selection
ConTaFL is introduced, a contrastive and tail-aware FL client selection framework that systematically addresses the aforementioned key challenges through coordinated mechanisms and consistently outperforms state-of-the-art FL frameworks across diverse noisy and non-IID settings while improving global model robustness a...
Fahmida Islam, Adnan Mahmood, Ying-Xun Wang et al.
· IEEE Open Journal of the Com... · 0 citations