Kusner, M; Russell, C; Loftus, J; Silva, R; (2019) Making Decisions that Reduce Discriminatory Impacts. In: Xing, E, (ed.) Proceedings of the 36th International Conference on Machine Learning (IML 2019). PMLR (Proceedings of Machine Learning Research): Long Beach, CA, USA.

Preview

Text kusner19a.pdf - Published Version Download (5MB) | Preview

Abstract

As machine learning algorithms move into realworld settings, it is crucial to ensure they are aligned with societal values. There has been much work on one aspect of this, namely the discriminatory prediction problem: How can we reduce discrimination in the predictions themselves? While an important question, solutions to this problem only apply in a restricted setting, as we have full control over the predictions. Often we care about the non-discrimination of quantities we do not have full control over. Thus, we describe another key aspect of this challenge, the discriminatory impact problem: How can we reduce discrimination arising from the real-world impact of decisions? To address this, we describe causal methods that model the relevant parts of the real-world system in which the decisions are made. Unlike previous approaches, these models not only allow us to map the causal pathway of a single decision, but also to model the effect of interference–how the impact on an individual depends on decisions made about other people. Often, the goal of decision policies is to maximize a beneficial impact overall. To reduce the discrimination of these benefits, we devise a constraint inspired by recent work in counterfactual fairness (Kusner et al., 2017), and give an efficient procedure to solve the constrained optimization problem. We demonstrate our approach with an example: how to increase students taking college entrance exams in New York City public schools.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item