Zhang, Jiang;
Beschastnikh, Ivan;
Mechtaev, Sergey;
Roychoudhury, Abhik;
(2022)
Fair Decision Making via Automated Repair of Decision Trees.
In:
2022 IEEE/ACM International Workshop on Equitable Data and Technology (FairWare 2022).
(pp. pp. 9-16).
IEEE (Institute of Electrical and Electronics Engineers)
Preview |
Text
Mechtaev_3524491.3527306.pdf Download (248kB) | Preview |
Abstract
Data-driven decision-making allows more resource allocation tasks to be done by programs. Unfortunately, real-life training datasets may capture human biases, and the learned models can be unfair. To resolve this, one could either train a new, fair model from scratch or repair an existing unfair model. The former approach is liable for unbounded semantic difference, hence is unsuitable for social or legislative decisions. Meanwhile, the scalability of state-of-the-art model repair techniques is unsatisfactory. In this paper, we aim to automatically repair unfair decision models by converting any decision tree or random forest into a fair one with respect to a specific dataset and sensitive attributes. We built the FairRepair tool, inspired by automated program repair techniques for traditional programs. It uses a MaxSMT solver to decide which paths in the decision tree could be flipped or refined, with both fairness and semantic difference as hard constraints. Our approach is sound and complete, and the output repair always satisfies the desired fairness and semantic difference requirements. FairRepair is able to repair an unfair decision tree on the well-known COMPAS dataset [2] in 1 minute on average, achieving 90.3% fairness and only 2.3% semantic difference. We compared FairRepair with 4 state-of-the-art fairness learning algorithms [10, 13, 16, 18]. While achieving similar fairness by training new models, they incur 8.9% to 13.5% semantic difference. These results show that FairRepair is capable of repairing an unfair model while maintaining the accuracy and incurring small semantic difference.
| Type: | Proceedings paper |
|---|---|
| Title: | Fair Decision Making via Automated Repair of Decision Trees |
| Event: | IEEE/ACM International Workshop on Equitable Data and Technology (FairWare) |
| Location: | Pittsburgh, PA |
| Dates: | 9 May 2022 |
| ISBN-13: | 9781450392921 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3524491.3527306 |
| Publisher version: | https://doi.org/10.1145/3524491.3527306 |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third-party material in this article are included in the Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
| Keywords: | algorithmic fairness, decision trees, automated program repair |
| UCL classification: | 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 UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10157280 |
Archive Staff Only
 |
View Item |
