解决联邦学习中恶意客户端谎报数据量的问题，提升模型准确率。
Local Data Quantity-Aware Weighted Averaging for Federated Learning with Dishonest Clients
- 根据客户端上传的梯度预测真实数据量，避免虚假申报影响聚合。
- 在三个基准数据集上，相比主流方法平均提升3.17%准确率。
- 可无缝集成到任意联邦学习框架，适合隐私保护场景使用。
联邦学习（FL）允许多个客户端协作训练深度学习模型，而无需将数据上传至服务器，从而保障客户端隐私。服务器端的聚合过程对最终模型性能至关重要。目前最常用的聚合方法是基于客户端数据量的加权平均，认为数据量能反映其贡献。然而，该方法易受模型偏差影响，因为恶意客户端可能虚报本地数据量，且服务器难以验证。为此，本文提出一种新型安全的联邦数据量感知加权平均方法（FedDua），能够基于客户端上传的局部模型梯度，准确预测其真实训练数据量。该方法可无缝集成到任何涉及服务器端模型聚合的联邦学习算法中。在三个基准数据集上的大量实验表明，当存在不准确的数据量声明时，FedDua相较于四种主流联邦聚合方法，平均提升全局模型性能3.17%。
原文摘要 · Abstract (English)
Federated learning (FL) enables collaborative training of deep learning models without requiring data to leave local clients, thereby preserving client privacy. The aggregation process on the server plays a critical role in the performance of the resulting FL model. The most commonly used aggregation method is weighted averaging based on the amount of data from each client, which is thought to reflect each client's contribution. However, this method is prone to model bias, as dishonest clients might report inaccurate training data volumes to the server, which is hard to verify. To address this issue, we propose a novel secure \underline{Fed}erated \underline{D}ata q\underline{u}antity-\underline{a}ware weighted averaging method (FedDua). It enables FL servers to accurately predict the amount of training data from each client based on their local model gradients uploaded. Furthermore, it can be seamlessly integrated into any FL algorithms that involve server-side model aggregation. Extensive experiments on three benchmarking datasets demonstrate that FedDua improves the global model performance by an average of 3.17% compared to four popular FL aggregation methods in the presence of inaccurate client data volume declarations.
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。