Federated Learning With Noisy and Imbalanced Data: A Contrastive Reliability-Based Framework for Long-Tail-Aware Client Selection

Abstract

Federated Learning (FL) client selection faces significant challenges in real-world deployments due to label noise, Non-Independent and Identically Distributed (Non-IID) data, long-tailed class distributions, unreliable client participation, and fairness constraints. These challenges become even more pronounced in Web of Things networks, wherein highly dynamic, resource-constrained clients operate under variable data quality and generate noisy, imbalanced, and non-IID data. In such settings, reliability-based client selection may inadvertently discard valuable knowledge associated with underrepresented tail-classes when informative clients are treated as unreliable. Accordingly, we introduce ConTaFL, a contrastive and tail-aware FL client selection framework, that systematically addresses the aforementioned key challenges through coordinated mechanisms. ConTaFL employs (a) contrastive representation divergence to address long-tailed class distributions, (b) an uncertainty-guided reliability-based weighting to dynamically identify and select reliable clients, (c) adaptive noise-resilient distillation to mitigate the impact of noisy updates, and (d) client rehabilitation to enable previously excluded clients to rejoin training once they surpass the predefined reliability threshold, thereby promoting fair participation across clients. Extensive experiments on CIFAR-10, CIFAR-100, MNIST, and TON-IoT datasets demonstrate that ConTaFL consistently outperforms state-of-the-art FL frameworks across diverse noisy and non-IID settings while improving global model robustness and tail-class representation.