Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation

Authors

  • Umang Gupta Information Sciences Institute, University of Southern California
  • Aaron M Ferber University of Southern California
  • Bistra Dilkina University of Southern California
  • Greg Ver Steeg Information Sciences Institute, University of Southern California

Keywords:

Representation Learning, Ethics -- Bias, Fairness, Transparency & Privacy

Abstract

Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between different groups in downstream applications. A naive solution is to transform the data so that it is statistically independent of group membership, but this may throw away too much information when a reasonable compromise between fairness and accuracy is desired. Another common approach is to limit the ability of a particular adversary who seeks to maximize parity. Unfortunately, representations produced by adversarial approaches may still retain biases as their efficacy is tied to the complexity of the adversary used during training. To this end, we theoretically establish that by limiting the mutual information between representations and protected attributes, we can assuredly control the parity of any downstream classifier. We demonstrate an effective method for controlling parity through mutual information based on contrastive information estimators and show that they outperform approaches that rely on variational bounds based on complex generative models. We test our approach on UCI Adult and Heritage Health datasets and demonstrate that our approach provides more informative representations across a range of desired parity thresholds while providing strong theoretical guarantees on the parity of any downstream algorithm.

Downloads

Published

2021-05-18

How to Cite

Gupta, U., Ferber, A. M., Dilkina, B., & Ver Steeg, G. (2021). Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 7610-7619. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16931

Issue

Section

AAAI Technical Track on Machine Learning II