Publications
Publications
- Advances in Neural Information Processing Systems (NeurIPS)
Towards Robust and Reliable Algorithmic Recourse
By: Sohini Upadhyay, Shalmali Joshi and Himabindu Lakkaraju
Abstract
As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan
approvals), there has been growing interest in post-hoc techniques which provide recourse to affected
individuals. These techniques generate recourses under the assumption that the underlying predictive
model does not change. However, in practice, models are often regularly updated for a variety of
reasons (e.g., dataset shifts), thereby rendering previously prescribed recourses ineffective. To address
this problem, we propose a novel framework, RObust Algorithmic Recourse (ROAR), that leverages
adversarial training for finding recourses that are robust to model shifts. To the best of our knowledge,
this work proposes the first ever solution to this critical problem. We also carry out detailed theoretical
analysis which underscores the importance of constructing recourses that are robust to model shifts:
1) we derive a lower bound on the probability of invalidation of recourses generated by existing
approaches which are not robust to model shifts. 2) we prove that the additional cost incurred due
to the robust recourses output by our framework is bounded. Experimental evaluation on multiple
synthetic and real-world datasets demonstrates the efficacy of the proposed framework and supports
our theoretical findings.
Keywords
Citation
Upadhyay, Sohini, Shalmali Joshi, and Himabindu Lakkaraju. "Towards Robust and Reliable Algorithmic Recourse." Advances in Neural Information Processing Systems (NeurIPS) 34 (2021).