Fair ML in Budget-Constrained Decision Making

Fairness in Machine Learning. Motivation, background and research question.
[Bak19F] Presented at KDD 2019 Explainable AI (XAI) for Accountability, Fairness, and Transparency Workshop.
[Bak19D]. Presented at NeurIPS 2019 Human-Centric Machine Learning Workshop.

References

[Bak19F]

On Fairness in Budget-Constrained Decision Making, Michiel A Bakker, Alejandro Noriega-Campero, Duy Patrick Tu, Prasanna Sattigeri, Kush R Varshney.

Aug 2019

The machine learning community and society at large have become increasingly concerned with discrimination and bias in data-driven decision making systems. This has led to a dramatic increase in academic and popular interest in algorithmic fairness. In this work, we focus on fairness in budget-constrained decision making, where the goal is to acquire information (features) one-by-one for each …

Publication

[Bak19D]

DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning, M. Bakker, Duy Patrick Tu, Humberto Riverón Valdés, K. Gummadi, Kush R. Varshney, Adrian Weller, A. Pentland.

2019

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 …

Publication