BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring

TL;DR

BiFedKD is a novel federated knowledge distillation framework designed to improve ECG monitoring accuracy under non-IID and long-tailed data distributions, while reducing communication and computation costs.

Contribution

The paper introduces a bidirectional federated knowledge distillation method with an aggregation-by-distillation pipeline and temperature scaling for ECG data.

Findings

BiFedKD improves accuracy and Macro-F1 by 3.52% and 9.93% over baseline.

Reduces communication overhead by 40% and computation cost by 71.7%.

Effective under non-IID and long-tailed ECG data distributions.

Abstract

Electrocardiogram (ECG) monitoring in Internet of Medical Things (IoMT) networks is constrained by strict data-sharing regulations and privacy concerns. Federated learning (FL) enables collaborative learning by keeping raw ECG data on devices, but frequent transmissions of high-dimensional model updates incur heavy per-round traffic over bandwidth-limited links. To alleviate this bottleneck, federated distillation (FD) replaces parameter exchange with logit-based knowledge transfer. However, the performance of FD often degrades under the non-independent and identically distributed (non-IID) and long-tailed label distributions in ECG deployments. To address these challenges, we propose a bidirectional federated knowledge distillation (BiFedKD) framework that employs an aggregation-by-distillation pipeline with temperature scaling to produce a stable global distillation signal for cross-client alignment. Experiments on the MIT-BIH Arrhythmia dataset show that BiFedKD improves accuracy and Macro-F1 over the baseline by $3.52\%$ and $9.93\%$, respectively. Moreover, to reach the same Macro-F1, BiFedKD reduces communication overhead by $40\%$ and computation cost by $71.7\%$ compared with the baseline.