Fairness and causality in machine learning

Counterfactual fairness formulates fair machine learning within a causal inference perspective, motivated by the intuition that defining or verifying fairness is a similar challenge to determining causality.

Author

Joshua Loftus

Published

February 17, 2022

Causal inference in fairness

This work approaches fair machine learning from a causal inference perspective, arguing that determining what is fair is a similar challenge to determining causality.

Press

Some of this work was covered in the New Scientist and 36Kr.

Publications

  • L. E. J. Bynum, J. R. Loftus, J. Stoyanovich, Disaggregated Interventions to Reduce Inequality. Equity and Access in Algorithms, Mechanisms, and Optimization, 2021. [link]

  • K. Yang, J. R. Loftus, J. Stoyanovich, Causal intersectionality and fair ranking. Foundations of Responsible Computing, 2021. [link]

  • M. J. Kusner, C. Russell, J. R. Loftus, R. Silva. Making Decisions that Reduce Discriminatory Impact. International Conference on Machine Learning, 2019. [link]

  • M. J. Kusner, J. R. Loftus, C. Russell, R. Silva. Counterfactual fairness. Advances in Neural Information Processing Systems, 2017. [link]

  • C. Russell, M. J. Kusner, J. R. Loftus, R. Silva. When worlds collide: integrating different counterfactual assumptions in fairness. Advances in Neural Information Processing Systems, 2017. [link]

  • J. R. Loftus, C. Russell, M. J. Kusner, R. Silva. Causal reasoning for algorithmic fairness. Preprint.