Mechanisms for Data Sharing in Collaborative Causal Inference (Extended Version)
This addresses the challenge of equitable data sharing in federated learning for causal inference, particularly in domains like healthcare, but is incremental as it builds on existing methods.
The paper tackles the problem of incentivizing data sharing among self-interested parties in collaborative causal inference by developing a data valuation scheme that measures each party's contribution based on causal structures, enabling fair rewards or maximized contributions.
Collaborative causal inference (CCI) is a federated learning method for pooling data from multiple, often self-interested, parties, to achieve a common learning goal over causal structures, e.g. estimation and optimization of treatment variables in a medical setting. Since obtaining data can be costly for the participants and sharing unique data poses the risk of losing competitive advantages, motivating the participation of all parties through equitable rewards and incentives is necessary. This paper devises an evaluation scheme to measure the value of each party's data contribution to the common learning task, tailored to causal inference's statistical demands, by comparing completed partially directed acyclic graphs (CPDAGs) inferred from observational data contributed by the participants. The Data Valuation Scheme thus obtained can then be used to introduce mechanisms that incentivize the agents to contribute data. It can be leveraged to reward agents fairly, according to the quality of their data, or to maximize all agents' data contributions.