AI 中文总结
该研究通过将经典外部性机制适配联邦学习场景，对比了夏普利值机制与外部性机制在社会最优性、个体理性等维度的表现，揭示了互惠公平与社会效率的权衡关系。
AI 中文摘要
联邦学习（FL）需要有效的激励机制来激励数据共享并防止策略性搭便车。近期的联邦学习机制如夏普利值机制M^Shap能保证智能体间的互惠公平，但在现实独立外部选项下，这类机制如何影响社会最优性和个体理性的完整分析仍未知。本文通过将经典外部性机制M^E适配到联邦学习场景，填补了这一空白。我们从社会最优性、个体理性、公平性/互惠性三个维度对比了M^Shap和M^E：首先，我们证实M^Shap通常无法最大化社会福利，因为其边际激励会驱动智能体过度贡献资源，而M^E的设计目标就是最大化社会福利；其次，我们通过考虑智能体以自身数据进行独立训练作为外部选项时的个体理性缺口来评估参与激励，发现两种机制在同构场景下均能保证个体理性，进一步表明在温和条件下，M^E在智能体异质性下仍能维持该保证，而M^Shap则不能；最后，我们证明M^Shap的设计目标是维持完美互惠，而M^E通常无法做到，仅在同构场景下的对称均衡处保证个体收益与夏普利贡献匹配，因为它会牺牲个体公平以在异质性下最大化集体福利。实证模拟验证了我们的理论发现，阐明了互惠公平与社会效率间存在权衡。
英文摘要
Federated learning (FL) requires effective incentive mechanisms to motivate data sharing and prevent strategic free-riding. Recent FL mechanisms such as the Shapley value mechanism M^Shap guarantee reciprocal fairness for agents. However, a complete analysis of how such mechanisms impact social optimality and individual rationality under realistic, standalone outside options remains unknown. In this paper, we address this gap by adapting the classical Externality mechanism M^E to the federated learning setting. We conduct a comparison of M^Shap and M^E across three dimensions: social optimality, individual rationality, and fairness/reciprocity. First, we establish that M^Shap generally does not maximize social welfare because its marginal incentives drive agents to over-contribute resources, while M^E maximizes social welfare by design. Second, we evaluate participation incentives through the individual rationality gap when considering agents' outside options as standalone training on their own data. We find that both mechanisms ensure individual rationality in homogeneous settings. We further show that under mild conditions, M^E maintains this guarantee under agent heterogeneity, whereas M^Shap does not. Third, we demonstrate that while M^Shap maintains perfect reciprocity by design, M^E generally does not, and only ensures that individual benefits match Shapley contributions at symmetric equilibria under homogeneity, as it sacrifices individual fairness to maximize collective welfare under heterogeneity. Empirical simulations validate our theoretical findings and illustrate a tradeoff between reciprocal fairness and social efficiency.
CommentsExtended version (with full proofs) of a paper accepted at GameSec 2026. 29 pages, 5 figures
