Incentives in Private Collaborative Machine Learning

TL;DR

This paper proposes a novel incentive mechanism for collaborative machine learning that incorporates differential privacy, balancing privacy guarantees with model utility, and rewards participants with privacy-preserving posterior samples.

Contribution

It introduces a differential privacy-based valuation method that incentivizes truthful participation while maintaining privacy and fairness in collaborative learning.

Findings

Effective privacy-utility trade-off achieved

Participants are deterred from excessive privacy guarantees

Method demonstrated successfully on synthetic and real datasets

Abstract

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce differential privacy (DP) as an incentive. Each party can select its required DP guarantee and perturb its sufficient statistic (SS) accordingly. The mediator values the perturbed SS by the Bayesian surprise it elicits about the model parameters. As our valuation function enforces a privacy-valuation trade-off, parties are deterred from selecting excessive DP guarantees that reduce the utility of the grand coalition's model. Finally, the mediator rewards each party with different posterior samples of the model parameters. Such rewards still satisfy existing incentives like fairness but additionally preserve DP and a high similarity to the grand coalition's posterior. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets.