多方机器学习的机制设计
Mechanism Design for Multi-Party Machine Learning
摘要：
在多方机器学习系统中，各方通过以隐私保护的方式共享数据来合作优化更好的模型。学习中的一个主要挑战是激励问题。例如，如果各方之间存在竞争，则可以策略性地隐藏他的数据以防止其他方获得更好的模型。本文从机制设计的角度来研究这一问题，并结合多方学习的特点。首先，每个代理人的估值都有外部性，依赖于其他人的类型和行为。第二，每个代理人只能误报一个低于他的真实类型的类型，而不是相反。我们称这种设置为依赖类型动作空间的相互依赖值。我们提供了最佳的真实机制，在准单调效用设置。我们还提供了在最一般的情况下真实机制的必要和充分条件。最后，我们发现这种机制的存在是高度受市场增长率的影响，并提供实证分析。
英文摘要：
In a multi-party machine learning system, different parties cooperate on optimizing towards better models by sharing data in a privacy-preserving way. A major challenge in learning is the incentive issue. For example, if there is competition among the parties, one may strategically hide his data to prevent other parties from getting better models. In this paper, we study the problem through the lens of mechanism design and incorporate the features of multi-party learning in our setting. First, each agent's valuation has externalities that depend on others' types and actions. Second, each agent can only misreport a type lower than his true type, but not the other way round. We call this setting interdependent value with type-dependent action spaces. We provide the optimal truthful mechanism in the quasi-monotone utility setting. We also provide necessary and sufficient conditions for truthful mechanisms in the most general case. Finally, we show the existence of such mechanisms is highly affected by the market growth rate and provide empirical analysis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
