Timezone: »
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 theoretical analysis which underscores the importance of constructing recourses that are robust to model shifts: 1) We quantify the probability of invalidation for recourses generated without accounting for 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.
Author Information
Sohini Upadhyay (IBM Research)
Shalmali Joshi (Harvard University (SEAS))
Himabindu Lakkaraju (Stanford University)
More from the Same Authors
-
2022 : Metric Elicitation; Moving from Theory to Practice »
Safinah Ali · Sohini Upadhyay · Gaurush Hiranandani · Elena Glassman · Sanmi Koyejo -
2022 : "Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts »
Haoran Zhang · Harvineet Singh · Marzyeh Ghassemi · Shalmali Joshi -
2021 Poster: Reliable Post hoc Explanations: Modeling Uncertainty in Explainability »
Dylan Slack · Anna Hilgard · Sameer Singh · Himabindu Lakkaraju -
2021 Poster: Learning Models for Actionable Recourse »
Alexis Ross · Himabindu Lakkaraju · Osbert Bastani -
2021 Poster: Counterfactual Explanations Can Be Manipulated »
Dylan Slack · Anna Hilgard · Himabindu Lakkaraju · Sameer Singh -
2020 Poster: What went wrong and when? Instance-wise feature importance for time-series black-box models »
Sana Tonekaboni · Shalmali Joshi · Kieran Campbell · David Duvenaud · Anna Goldenberg -
2016 Poster: Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making »
Himabindu Lakkaraju · Jure Leskovec