UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

Russell, C; Kusner, M; Loftus, C; Silva, R; (2017) When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness. In: Guyon, I and Luxburg, UV and Bengio, S and Wallach, H and Fergus, R and Vishwanathan, S and Garnett, R, (eds.) Advances in Neural Information Processing Systems 30 (NIPS 2017). NIPS Proceedings: Long Beach, CA, USA. Green open access

[thumbnail of 7220-when-worlds-collide-integrating-different-counterfactual-assumptions-in-fairness.pdf]
Preview
Text
7220-when-worlds-collide-integrating-different-counterfactual-assumptions-in-fairness.pdf - Accepted Version

Download (663kB) | Preview

Abstract

Machine learning is now being used to make crucial decisions about people's lives. For nearly all of these decisions there is a risk that individuals of a certain race, gender, sexual orientation, or any other subpopulation are unfairly discriminated against. Our recent method has demonstrated how to use techniques from counterfactual inference to make predictions fair across different subpopulations. This method requires that one provides the causal model that generated the data at hand. In general, validating all causal implications of the model is not possible without further assumptions. Hence, it is desirable to integrate competing causal models to provide counterfactually fair decisions, regardless of which causal "world" is the correct one. In this paper, we show how it is possible to make predictions that are approximately fair with respect to multiple possible causal models at once, thus mitigating the problem of exact causal specification. We frame the goal of learning a fair classifier as an optimization problem with fairness constraints entailed by competing causal explanations. We show how this optimization problem can be efficiently solved using gradient-based methods. We demonstrate the flexibility of our model on two real-world fair classification problems. We show that our model can seamlessly balance fairness in multiple worlds with prediction accuracy.

Type: Proceedings paper
Title: When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness
Event: Neural Information Processing Systems 2017
Dates: 04 December 2017 - 09 December 2017
Open access status: An open access version is available from UCL Discovery
Publisher version: https://papers.nips.cc/paper/7220-when-worlds-coll...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10038510
Downloads since deposit
158Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item