Fair Multi-party Machine Learning -- a Game Theoretic approach
This addresses the challenge of incentivizing data sharing in multi-party ML for entities like governments or businesses, though it is incremental in applying game theory to this context.
The paper tackles the problem of ensuring fair and stable collaboration among profit-driven data providers for machine learning by modeling data sharing as a cooperative game, and it theoretically analyzes optimal outcomes and their sensitivity, with experiments providing insights on data valuation.
High performance machine learning models have become highly dependent on the availability of large quantity and quality of training data. To achieve this, various central agencies such as the government have suggested for different data providers to pool their data together to learn a unified predictive model, which performs better. However, these providers are usually profit-driven and would only agree to participate inthe data sharing process if the process is deemed both profitable and fair for themselves. Due to the lack of existing literature, it is unclear whether a fair and stable outcome is possible in such data sharing processes. Hence, we wish to investigate the outcomes surrounding these scenarios and study if data providers would even agree to collaborate in the first place. Tapping on cooperative game concepts in Game Theory, we introduce the data sharing process between a group of agents as a new class of cooperative games with modified definition of stability and fairness. Using these new definitions, we then theoretically study the optimal and suboptimal outcomes of such data sharing processes and their sensitivity to perturbation.Through experiments, we present intuitive insights regarding theoretical results analysed in this paper and discuss various ways in which data can be valued reasonably.