CounteRGAN: Generating Counterfactuals for Real-Time Recourse and Interpretability using Residual GANs

Daniel Alexander Nemirovsky, Nicolas Kevin Thiebaut, Ye Xu, Abhishek Gupta

Keywords: machine learning, deep learning, generative adversarial networks, counterfactuals, machine learning interpretability, explainable artificial intelligence

TL;DR: This paper describes a novel method to produce counterfactuals using residual generative adversarial networks that are useful for providing real-time recourse and interpretability to users of predictive systems.

Abstract: Model interpretability, fairness, and recourse for end users have increased as machine learning models have become increasingly popular in areas including criminal justice, finance, healthcare, and job marketplaces. This work presents a novel method of addressing these issues by producing meaningful counterfactuals that are aimed at providing recourse to users and highlighting potential model biases. A meaningful counterfactual is a reasonable alternative scenario that illustrates how input data perturbations can influence the model's output. The CounteRGAN method generates meaningful counterfactuals for a target classifier by utilizing a novel Residual Generative Adversarial Network (RGAN). We compare our method against leading state-of-the-art approaches on image and tabular datasets over a variety of performance metrics. The results indicate a significant improvement over existing techniques in combined metric performance, with a latency reduction of 2 to 7 orders of magnitude which enables providing real-time recourse to users. The code for reproducibility can be found here: https://github.com/gan-counterfactuals/countergan.