用轨迹谢尔普利值实现联邦学习中客户端贡献的动态公平分配
Fairness-Aware Federated Learning with Trajectory Shapley Value
- 基于验证的时序效用评估客户端对全局优化轨迹的影响
- 在多个基准数据集上加速收敛并提升模型鲁棒性
- 适合关注公平性与对抗性参与的联邦学习研究者
联邦学习是一种新兴的分布式范式，应对异构且隐私敏感的数据挑战。它允许多个客户端通过在服务器端聚合本地更新协同训练模型。然而，传统聚合方法通常使用固定权重，无法反映客户端贡献的不均等和时变性，导致学习过程出现偏差和不稳定。为提升公平性与稳定性，我们提出轨迹谢尔普利值（TSV），一种基于验证、时间一致的效用度量，用于评估每个客户端对全局模型优化轨迹的影响。基于TSV，我们设计了FedTSV，一种自适应聚合方法，将每轮评估转化为动态客户端权重，使服务器能实时响应异构及对抗性参与。实验表明，FedTSV在多个基准数据集上加速收敛、提升鲁棒性，并实现更公平的贡献评估，为公平感知的联邦优化提供了理论基础。
原文摘要 · Abstract (English)
Federated learning is an emerging distributed paradigm that addresses the challenges posed by heterogeneous, privacy-sensitive data. It enables multiple clients to train a model collaboratively by aggregating their local updates at a server. However, conventional aggregation schemes typically use fixed weights that fail to reflect unequal and time-varying client contributions, leading to biased and unstable learning. To improve fairness and stability, we propose the Trajectory Shapley Value (TSV), a contribution metric that evaluates how each client influences the optimization trajectory of the global model using a validation-based, temporally consistent utility. Building on TSV, we design FedTSV, an adaptive aggregation method that converts per-round evaluations into dynamic client weights, allowing the server to respond to heterogeneous and adversarial participation in real time. Experiments on benchmark datasets show that FedTSV accelerates convergence, improves robustness, and yields more equitable contribution assessments, thereby providing a principled foundation for fairness-aware federated optimization.
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。