为去中心化联邦学习设计贡献评估方法，解决无中心节点下的激励难题。
How to Evaluate Participant Contributions in Decentralized Federated Learning
- 通过追踪每轮本地贡献的传播路径，量化客户端真实影响。
- 在大规模场景下逼近真实贡献值，且对恶意客户端保持鲁棒。
- 仅需本地上报数据，轻量级协调节点即可完成评估，适合实际部署。
联邦学习（FL）使多个客户端在不共享本地数据的情况下协同训练模型。其中，去中心化联邦学习（DFL）通过客户端间直接交换模型，避免了中心节点的通信瓶颈，受到关注。准确评估参与者贡献对激励积极协作、提升透明度至关重要。然而，现有贡献评估方法基于中心化设定，无法直接应用于DFL，主要因两大挑战：客户端无法访问非邻接客户端的模型，且难以追踪贡献随时间在点对点模型交换中的传播过程。为此，本文提出TRIP-Shapley，一种针对DFL的新型贡献评估方法。该方法通过追踪各轮本地贡献的传播路径，精准反映延迟与渐进式的影响传播。其优势在于，仅依赖客户端本地可观测的贡献报告，无需收集完整模型，由轻量级协调节点完成整体贡献估算。实验表明，TRIP-Shapley在逼近真实Shapley值方面表现优异，具备可扩展性，且在存在恶意客户端时仍具鲁棒性。
原文摘要 · Abstract (English)
Federated learning (FL) enables multiple clients to collaboratively train machine learning models without sharing local data. In particular, decentralized FL (DFL), where clients exchange models without a central server, has gained attention for mitigating communication bottlenecks. Evaluating participant contributions is crucial in DFL to incentivize active participation and enhance transparency. However, existing contribution evaluation methods for FL assume centralized settings and cannot be applied directly to DFL due to two challenges: the inaccessibility of each client to non-neighboring clients' models, and the necessity to trace how contributions propagate in conjunction with peer-to-peer model exchanges over time. To address these challenges, we propose TRIP-Shapley, a novel contribution evaluation method for DFL. TRIP-Shapley formulates the clients' overall contributions by tracing the propagation of the round-wise local contributions. In this way, TRIP-Shapley accurately reflects the delayed and gradual influence propagation, as well as allowing a lightweight coordinator node to estimate the overall contributions without collecting models, but based solely on locally observable contributions reported by each client. Experiments demonstrate that TRIP-Shapley is sufficiently close to the ground-truth Shapley value, is scalable to large-scale scenarios, and remains robust in the presence of dishonest clients.
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。