通过自适应选客户端提升联邦学习效率与隐私安全
Efficient Client Selection in Federated Learning
- 根据性能和系统限制动态选择客户端，结合差分隐私加噪
- 网络异常检测准确率提升7%，训练时间减少25%
- 兼顾容错性，适合对隐私和稳定性要求高的场景
联邦学习在保护数据隐私的同时实现分布式机器学习。本文提出一种融合差分隐私与容错能力的新型客户端选择框架。自适应客户端选择根据性能与系统约束动态调整参与客户端数量，并通过添加噪声保障隐私。在UNSW-NB15和ROAD数据集上的网络异常检测任务中，该方法相比基线模型准确率提升7%，训练时间减少25%。容错机制增强了系统鲁棒性，性能损失极小。
原文摘要 · Abstract (English)
Federated Learning (FL) enables decentralized machine learning while preserving data privacy. This paper proposes a novel client selection framework that integrates differential privacy and fault tolerance. The adaptive client selection adjusts the number of clients based on performance and system constraints, with noise added to protect privacy. Evaluated on the UNSW-NB15 and ROAD datasets for network anomaly detection, the method improves accuracy by 7% and reduces training time by 25% compared to baselines. Fault tolerance enhances robustness with minimal performance trade-offs.
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。