DART让联邦学习更抗干扰，服务器端插件零成本提升鲁棒性。
DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning
- 服务器端部署的无数据依赖插件，不增加客户端负担。
- 在多个数据集上显著提升模型对噪声、模糊等常见退化的鲁棒性。
- 适合资源受限的边缘设备场景，可无缝集成现有联邦学习系统。
联邦学习（FL）作为一种分布式机器学习算法，在保护数据隐私的同时训练边缘设备上的模型。然而，由于客户端计算资源受限，且对噪声、模糊和天气等常见退化缺乏鲁棒性，现有联邦学习系统面临挑战。现有的鲁棒训练方法计算开销大，不适合资源受限的客户端。本文提出一种全新的、与数据无关的鲁棒训练插件DART，可部署于任意联邦学习系统中，在服务器端增强模型鲁棒性，且客户端无需额外计算开销。DART不访问私有数据，确保了与现有系统的无缝集成。大量实验表明，DART能有效提升先进联邦学习系统在多种退化条件下的表现，是实际部署中兼具实用性与可扩展性的解决方案。
原文摘要 · Abstract (English)
Federated learning (FL) emerged as a popular distributed algorithm to train machine learning models on edge devices while preserving data privacy. However, FL systems face challenges due to client-side computational constraints and from a lack of robustness to naturally occurring common corruptions such as noise, blur, and weather effects. Existing robust training methods are computationally expensive and unsuitable for resource-constrained clients. We propose a novel data-agnostic robust training (DART) plug-in that can be deployed in any FL system to enhance robustness at zero client overhead. DART operates at the server-side and does not require private data access, ensuring seamless integration in existing FL systems. Extensive experiments showcase DART's ability to enhance robustness of state-of-the-art FL systems, establishing it as a practical and scalable solution for real-world robust FL deployment.
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。