让参与联邦学习的各方主动贡献数据，同时保证模型效果。
Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation
- 客户端上报参数和动态调整的数据量，激励真实参与。
- 在凸与非凸目标下均能保证模型性能，收敛稳定。
- 适合关注长期合作与激励机制的研究者或工业应用。
联邦学习（FL）是一种通信高效的协作学习框架，可在多个拥有私有本地数据集的智能体间协同训练模型。尽管FL在提升全局模型性能方面已被广泛证实，但各参与方可能出于自身利益，权衡学习收益与数据贡献成本而采取策略行为。为解决这一问题，本文提出一种激励感知的联邦平均方法：每轮通信中，客户端不仅上传本地模型参数，还上报经动态调整的训练数据规模。该数据规模通过纳什均衡寻求更新规则进行调节，以反映策略性数据参与行为。本文在凸与非凸全局目标设定下分析了所提方法，并建立了激励感知联邦学习算法的性能保证。此外，在仅单调博弈设定下，引入福利损失最小化框架，证明了该方案的渐近收敛性。在MNIST与CIFAR-10数据集上的数值实验表明，各客户端在实现具有竞争力的全局模型性能的同时，能够收敛至稳定的参与策略。
原文摘要 · Abstract (English)
Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with private local datasets. While the benefits of FL in improving global model performance are well established, individual agents may behave strategically, balancing the learning payoff against the cost of contributing their local data. Motivated by the need for FL frameworks that successfully retain participating agents, we propose an incentive-aware federated averaging method in which, at each communication round, clients transmit both their local model parameters and their updated training dataset sizes to the server. The dataset sizes are dynamically adjusted via a Nash equilibrium (NE)-seeking update rule that captures strategic data participation. We analyze the proposed method under convex and nonconvex global objective settings and establish performance guarantees for the resulting incentive-aware FL algorithm. Furthermore, under a merely monotone game setting, we consider a welfare loss minimization framework and establish asymptotic convergence of the scheme. Numerical experiments on the MNIST and CIFAR-10 datasets demonstrate that agents achieve competitive global model performance while converging to stable data participation strategies.
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。