CUED Publications database

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning

Bakker, MA and Tu, DP and Valdés, HR and Gummadi, KP and Varshney, KR and Weller, A and Pentland, A DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning. (Unpublished)

Full text not available from this repository.


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

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG cs.CY stat.ML
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 14 Nov 2019 02:18
Last Modified: 18 Feb 2021 18:14