DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
This work addresses fairness in dynamic information discovery for machine learning applications, but it is incremental as it builds on adversarial representation learning.
The authors tackled the problem of dynamically selecting feature subsets to balance predictive accuracy and fairness, specifically demographic parity, in scenarios with unknown third-party objectives. They demonstrated empirically on two real-world datasets that their framework can trade-off fairness and predictive performance.
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness of predictors downstream. Based on the set of already acquired features, the agent decides dynamically to either collect more information from the set of available features or to stop and predict using the information that is currently available. Building on previous work exploring adversarial representation learning, we attain group fairness (demographic parity) by rewarding the agent with the adversary's loss, computed over the final feature set. Importantly, however, the framework provides a more general starting point for fair or private dynamic information discovery. Finally, we demonstrate empirically, using two real-world datasets, that we can trade-off fairness and predictive performance