Ensuring Actionable Recourse via Adversarial Training

11/12/2020
by   Alexis Ross, et al.
0

As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations provide individuals adversely impacted by predicted outcomes (e.g., an applicant denied a loan) with "recourse" —i.e., a description of how they can change their features to obtain a positive outcome. We propose a novel algorithm that leverages adversarial training and PAC confidence sets to learn models that theoretically guarantee recourse to affected individuals with high probability without sacrificing accuracy. To the best of our knowledge, our approach is the first to learn models for which recourses are guaranteed with high probability. Extensive experimentation with real world datasets spanning various applications including recidivism prediction, bail outcomes, and lending demonstrate the efficacy of the proposed framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/26/2021

Towards Robust and Reliable Algorithmic Recourse

As predictive models are increasingly being deployed in high-stakes deci...
research
11/12/2020

Robust and Stable Black Box Explanations

As machine learning black boxes are increasingly being deployed in real-...
research
09/18/2020

Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis

We propose a novel approach to understanding the decision making of comp...
research
09/15/2020

Interpretable and Interactive Summaries of Actionable Recourses

As predictive models are increasingly being deployed in high-stakes deci...
research
03/13/2022

Algorithmic Recourse in the Face of Noisy Human Responses

As machine learning (ML) models are increasingly being deployed in high-...
research
07/06/2022

PAC Prediction Sets for Meta-Learning

Uncertainty quantification is a key component of machine learning models...

Please sign up or login with your details

Forgot password? Click here to reset