Collaborative Machine Learning with Incentive-Aware Model Rewards

TL;DR

This paper introduces an incentive-aware reward scheme for collaborative machine learning that fairly values each party's contribution using Shapley value and information gain, promoting fair and stable collaboration.

Contribution

It proposes a novel model reward scheme based on cooperative game theory principles, incorporating Gaussian noise to ensure fairness and incentivize data sharing.

Findings

The scheme achieves fairness and stability in model rewards.

Empirical results demonstrate effective incentive alignment.

The approach performs well on synthetic and real datasets.

Abstract

Collaborative machine learning (ML) is an appealing paradigm to build high-quality ML models by training on the aggregated data from many parties. However, these parties are only willing to share their data when given enough incentives, such as a guaranteed fair reward based on their contributions. This motivates the need for measuring a party's contribution and designing an incentive-aware reward scheme accordingly. This paper proposes to value a party's reward based on Shapley value and information gain on model parameters given its data. Subsequently, we give each party a model as a reward. To formally incentivize the collaboration, we define some desirable properties (e.g., fairness and stability) which are inspired by cooperative game theory but adapted for our model reward that is uniquely freely replicable. Then, we propose a novel model reward scheme to satisfy fairness and trade off between the desirable properties via an adjustable parameter. The value of each party's model reward determined by our scheme is attained by injecting Gaussian noise to the aggregated training data with an optimized noise variance. We empirically demonstrate interesting properties of our scheme and evaluate its performance using synthetic and real-world datasets.