Quantifying the Endogenous Domain and Model Shifts Induced by the DiCE Generator

Bachelor Thesis (2022)
Author(s)

A.J. Buszydlik (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Cynthia C. S. Liem – Mentor (TU Delft - Multimedia Computing)

Patrick Altmeyer – Mentor (TU Delft - Multimedia Computing)

Gosia Migut – Graduation committee member (TU Delft - Computer Science & Engineering-Teaching Team)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2022 Aleksander Buszydlik
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Aleksander Buszydlik
Graduation Date
23-06-2022
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project', 'Endogenous model shifts in algorithmic recourse']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Algorithmic recourse aims to provide individuals affected by a negative classification outcome with actions which, if applied, would flip this outcome. Various approaches to the generation of recourse have been proposed in the literature; these are typically assessed on statistical measures such as the validity of generated explanations or their proximity to the training data. However, little to no attention has been paid to the underlying dynamics of recourse. If a group of individuals applies the suggested actions, they may over time induce a shift in the domain or model. We propose a framework for the measurement of such intrinsic shifts, and conduct an analysis of the dynamics of recourse implemented by the generators proposed by Mothilal et al. and Wachter et al.. Our results suggest that the application of recourse is likely to introduce statistically significant shifts in the system, and that the underlying dataset and model impact the behavior of the generators.

Files

License info not available