Privacy-Preserving Algorithmic Recourse

TL;DR

This paper introduces PrivRecourse, a privacy-preserving method for generating realistic, actionable recourse paths in machine learning models using differentially private clustering and graph-based path generation.

Contribution

The work presents a novel end-to-end pipeline that combines differential privacy with graph-based recourse path generation, improving privacy and realism over existing methods.

Findings

PrivRecourse provides privacy-preserving recourse paths that are realistic and feasible.

It outperforms simple noise addition and synthetic data methods in privacy and realism.

Empirical results on finance datasets demonstrate effectiveness.

Abstract

When individuals are subject to adverse outcomes from machine learning models, providing a recourse path to help achieve a positive outcome is desirable. Recent work has shown that counterfactual explanations - which can be used as a means of single-step recourse - are vulnerable to privacy issues, putting an individuals' privacy at risk. Providing a sequential multi-step path for recourse can amplify this risk. Furthermore, simply adding noise to recourse paths found from existing methods can impact the realism and actionability of the path for an end-user. In this work, we address privacy issues when generating realistic recourse paths based on instance-based counterfactual explanations, and provide PrivRecourse: an end-to-end privacy preserving pipeline that can provide realistic recourse paths. PrivRecourse uses differentially private (DP) clustering to represent non-overlapping subsets of the private dataset. These DP cluster centers are then used to generate recourse paths by forming a graph with cluster centers as the nodes, so that we can generate realistic - feasible and actionable - recourse paths. We empirically evaluate our approach on finance datasets and compare it to simply adding noise to data instances, and to using DP synthetic data, to generate the graph. We observe that PrivRecourse can provide paths that are private and realistic.