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

The Sensitivity of Counterfactual Fairness to Unmeasured Confounding

Kilbertus, N; Ball, P; Kusner, M; Weller, A; Silva, R; (2019) The Sensitivity of Counterfactual Fairness to Unmeasured Confounding. In: Globerson, A and Silva, R, (eds.) Proceedings of the 35th Uncertainty in Artificial Intelligence Conference (UAI 2019). AUAI Press: Tel Aviv, Israel. Green open access

[img]
Preview
Text
Silva_VoR_213.pdf - Published version

Download (445kB) | Preview

Abstract

Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In no small part, this has been due to the fact that causal models allow one to simultaneously leverage data and expert knowledge to remove discriminatory effects from predictions. However, one of the primary assumptions in causal modeling is that you know the causal graph. This introduces a new opportunity for bias, caused by misspecifying the causal model. One common way for misspecification to occur is via unmeasured confounding: the true causal effect between variables is partially described by unobserved quantities. In this work we design tools to assess the sensitivity of fairness measures to this confounding for the popular class of non-linear additive noise models (ANMs). Specifically, we give a procedure for computing the maximum difference between two counterfactually fair predictors, where one has become biased due to confounding. For the case of bivariate confounding our technique can be swiftly computed via a sequence of closed-form updates. For multivariate confounding we give an algorithm that can be efficiently solved via automatic differentiation. We demonstrate our new sensitivity analysis tools in real-world fairness scenarios to assess the bias arising from confounding.

Type: Proceedings paper
Title: The Sensitivity of Counterfactual Fairness to Unmeasured Confounding
Event: Uncertainty in Artificial Intelligence Conference (UAI 2019), 22-25 July 2019, Tel Aviv, Israel
Location: Tel Aviv, Israel
Dates: 22 July 2019 - 25 July 2019
Open access status: An open access version is available from UCL Discovery
Publisher version: http://auai.org/uai2019/proceedings/papers/213.pdf
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 > 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/10084992
Downloads since deposit
2Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item