解决医疗心电图联邦学习中的数据不均衡问题，提升模型精度与通信效率。
BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring
- 双向知识蒸馏机制，通过温度缩放稳定全局知识信号。
- 在MIT-BIH数据集上准确率提升3.52%，宏平均F1提高9.93%。
- 适合资源受限的医疗物联网场景，显著降低通信与计算开销。
物联网医疗网络中的心电图（ECG）监测受严格数据共享法规和隐私顾虑制约。联邦学习（FL）通过将原始数据保留在设备端实现协作学习，但高频传输高维模型更新会加剧带宽受限链路的通信负担。为缓解此瓶颈，联邦蒸馏（FD）以基于logit的知识传递替代参数交换。然而，在真实部署中非独立同分布（non-IID）和长尾标签分布常导致FD性能下降。为此，本文提出双向联邦知识蒸馏（BiFedKD）框架，采用聚合-蒸馏流水线结合温度缩放，生成稳定的全局蒸馏信号以促进跨客户端对齐。在MIT-BIH心律失常数据集上的实验表明，BiFedKD相比基线使准确率提升3.52%，宏平均F1提升9.93%；且达到相同宏平均F1时，通信开销减少40%，计算成本降低71.7%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。