No abstract

In this paper, we propose a novel federated learning (FL) framework for wireless Internet of Medical Things (IoMT) based healthcare systems, where multiple mobile clients and one edge server (ES) collaboratively train a shared model on long-tail data through wireless channels. However, the presence of long-tailed data in this system may introduce a biased global model which fails to handle the tail classes. Additionally, the occurrence of severe fading in wireless channels may prevent mobile clients from successfully uploading local models to the ES, thereby excluding them from participating in the model aggregation. These situations adversely affect the performance of FL. To overcome these challenges, we propose a novel scoring aided FL framework that uses a scoringbased sampling strategy to select mobile clients with more tailed data and better transmission conditions to upload their local models. Specifically, we leverage the logits to explore the data distribution among local clients and propose a logits based scoring client selection method to alleviate the impact of long-tailed data. Moreover, we address the impact of severe fading by incorporating the channel state information (CSI) and data rate of clients into the logits based scoring and proposing a novel logits and model upload rate based client selection method. Experimental results demonstrate the effectiveness of our proposed framework. In particular, compared to the conventional FedAvg, the proposed framework can achieve accuracy gains ranging from 4.44% to 28.36% on the CIFAR-10-LT dataset with an imbalance factor (IF) of 50.