<i>Stragglers Reimagined:</i> Explainability-Driven Adaptive Federated Learning for Resource Constrained IoMT System

In this paper, we present FlexiFed, a framework designed to enhance Federated Learning (FL) by addressing the challenges of device inclusivity and data prioritization. FL systems typically exclude low-resource devices, known as stragglers, due to their limited computational power, leading to the loss of valuable and often unique data. Additionally, current FL systems lack transparency, making it difficult to prioritize the contributions of individual devices. FlexiFed overcomes these issues by enabling stragglers to share simplified outputs, such as predictions and key feature importance scores, instead of full model updates. This reduces their computational and communication burden. The framework integrates explainability techniques to identify and emphasize critical data, ensuring rare and significant contributions are prioritized during training. FlexiFed distinguishes itself from similar frameworks by combining hierarchical aggregation with explainability-driven prioritization, directly addressing the need for fairness and transparency in diverse and resource-constrained environments.