通过梯度更新与确定性算法，选更异构的客户端提升联邦学习准确率。
Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning
- 用梯度更新衡量客户端异构性，比传统方法更准确。
- 相比之前方法，最高提升47%的模型准确率。
- 适合数据分布差异大的场景，提升联邦学习稳定性。
联邦学习（FL）在分布式架构下让多个客户端协作训练全局机器学习模型，无需共享敏感本地数据。然而，由于客户端间存在统计异构性，FL的准确率常低于传统机器学习方法。现有工作尝试通过使用客户端模型的损失和偏置等更新来选择参与者以提升全局模型性能，但这些方法无法准确反映客户端的异构性，且选择过程非确定性。为此，我们提出Terraform——一种新型客户端选择方法，结合梯度更新与确定性选择算法，优先选择具有显著异构性的客户端进行重训练。该双路径策略使Terraform在准确率上相比先前方法最高提升47%。通过全面的消融实验与训练时间分析，验证了Terraform在效率与鲁棒性方面的优势。
原文摘要 · Abstract (English)
Federated Learning (FL) enables a distributed client-server architecture where multiple clients collaboratively train a global Machine Learning (ML) model without sharing sensitive local data. However, FL often results in lower accuracy than traditional ML algorithms due to statistical heterogeneity across clients. Prior works attempt to address this by using model updates, such as loss and bias, from client models to select participants that can improve the global model's accuracy. However, these updates neither accurately represent a client's heterogeneity nor are their selection methods deterministic. We mitigate these limitations by introducing Terraform, a novel client selection methodology that uses gradient updates and a deterministic selection algorithm to select heterogeneous clients for retraining. This bi-pronged approach allows Terraform to achieve up to 47 percent higher accuracy over prior works. We further demonstrate its efficiency through comprehensive ablation studies and training time analyses, providing strong justification for the robustness of Terraform.
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。