Mechanism Design for Multi-Party Machine Learning

Abstract

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.

arXiv comment22 pages, 4 figures

References in corpus (5)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Auctions with Severely Bounded Communication
• Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Cited by in corpus (4)

• A Comprehensive Survey of Incentive Mechanism for Federated Learning
• Estimation of Individual Device Contributions for Incentivizing Federated Learning
• Prior-Independent Auctions for the Demand Side of Federated Learning
• On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator