针对异步去中心化联邦学习中的持续客户端掉线问题，提出自适应重建策略提升系统鲁棒性。
Mitigating Persistent Client Dropout in Asynchronous Decentralized Federated Learning
- 基于客户端重建的自适应策略，缓解因信息不全导致的更新丢失问题。
- 在表格与图像数据上，三种异构场景下均有效恢复部分性能损失。
- 适合研究去中心化联邦学习鲁棒性及实际部署中应对设备掉线的场景。
本文研究异步去中心化联邦学习（DFL）中的持续客户端掉线问题。由于异步性和去中心化特性，各参与方间模型更新信息不透明，导致客户端掉线后难以恢复。现有方法无法充分应对该问题，且缺乏对学习轮次、数据分布等关键信息的访问。本文提出基于客户端重建的自适应策略，在引入局部正则化的前提下显著改善系统鲁棒性。实验在表格与图像数据集上验证，涵盖三种异步DFL算法及三种数据异构场景（iid、non-iid、class-focused non-iid）。结果表明，即使未精确重构缺失客户端数据，所提方法仍能有效缓解性能下降。同时讨论了当前局限并指明未来方向。
原文摘要 · Abstract (English)
We consider the problem of persistent client dropout in asynchronous Decentralized Federated Learning (DFL). Asynchronicity and decentralization obfuscate information about model updates among federation peers, making recovery from a client dropout difficult. Access to the number of learning epochs, data distributions, and all the information necessary to precisely reconstruct the missing neighbor's loss functions is limited. We show that obvious mitigations do not adequately address the problem and introduce adaptive strategies based on client reconstruction. We show that these strategies can effectively recover some performance loss caused by dropout. Our work focuses on asynchronous DFL with local regularization and differs substantially from that in the existing literature. We evaluate the proposed methods on tabular and image datasets, involve three DFL algorithms, and three data heterogeneity scenarios (iid, non-iid, class-focused non-iid). Our experiments show that the proposed adaptive strategies can be effective in maintaining robustness of federated learning, even if they do not reconstruct the missing client's data precisely. We also discuss the limitations and identify future avenues for tackling the problem of client dropout.
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。