用负向知识蒸馏提升医疗联邦学习的泛化能力
FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems
- 引入负向知识蒸馏，同时学习目标与非目标信息
- 在多个医疗数据集上准确率最高提升2.53%
- 适合隐私敏感的医疗场景，兼顾性能与合规性
本文提出FedKDX，一种基于负向知识蒸馏（NKD）的联邦学习框架，以解决医疗AI中存在的局限性。与仅关注正向知识传递的方法不同，FedKDX同时捕捉目标与非目标信息，提升模型在医疗应用中的泛化能力。该框架在统一架构中整合了传统知识蒸馏、对比学习和NKD，既保障隐私又降低通信开销。在SLEEP、UCI-HAR和PAMAP2等医疗数据集上的实验表明，其准确率最高比现有方法提升2.53%，收敛更快，且在非独立同分布（non-IID）数据下表现更优。理论分析验证了NKD在缓解分布式医疗数据统计异质性方面的有效性。该方法适用于符合HIPAA和GDPR等法规的隐私敏感医疗场景，为去中心化医疗环境提供了性能与实用性兼备的解决方案。代码与模型已公开于https://github.com/phamdinhdat-ai/Fed_2024。
原文摘要 · Abstract (English)
This paper introduces FedKDX, a federated learning framework that addresses limitations in healthcare AI through Negative Knowledge Distillation (NKD). Unlike existing approaches that focus solely on positive knowledge transfer, FedKDX captures both target and non-target information to improve model generalization in healthcare applications. The framework integrates multiple knowledge transfer techniques--including traditional knowledge distillation, contrastive learning, and NKD--within a unified architecture that maintains privacy while reducing communication costs. Through experiments on healthcare datasets (SLEEP, UCI-HAR, and PAMAP2), FedKDX demonstrates improved accuracy (up to 2.53% over state-of-the-art methods), faster convergence, and better performance on non-IID data distributions. Theoretical analysis supports NKD's contribution to addressing statistical heterogeneity in distributed healthcare data. The approach shows promise for privacy-sensitive medical applications under regulatory frameworks like HIPAA and GDPR, offering a balanced solution between performance and practical implementation requirements in decentralized healthcare settings. The code and model are available at https://github.com/phamdinhdat-ai/Fed_2024.
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。