CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
arXiv:2009.05199
Abstract
The prevalence of machine learning models in various industries has led to growing demands for model interpretability and for the ability to provide meaningful recourse to users. For example, patients hoping to improve their diagnoses or loan applicants seeking to increase their chances of approval. Counterfactuals can help in this regard by identifying input perturbations that would result in more desirable prediction outcomes. Meaningful counterfactuals should be able to achieve the desired outcome, but also be realistic, actionable, and efficient to compute. Current approaches achieve desired outcomes with moderate actionability but are severely limited in terms of realism and latency. To tackle these limitations, we apply Generative Adversarial Nets (GANs) toward counterfactual search. We also introduce a novel Residual GAN (RGAN) that helps to improve counterfactual realism and actionability compared to regular GANs. The proposed CounteRGAN method utilizes an RGAN and a target classifier to produce counterfactuals capable of providing meaningful recourse. Evaluations on two popular datasets highlight how the CounteRGAN is able to overcome the limitations of existing methods, including latency improvements of >50x to >90,000x, making meaningful recourse available in real-time and applicable to a wide range of domains.
arXiv comment15 pages
References in corpus (19)
- Conditional Generative Adversarial Nets
- Explaining and Harnessing Adversarial Examples
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Spectral Normalization for Generative Adversarial Networks
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Axiomatic Attribution for Deep Networks
- European Union regulations on algorithmic decision-making and a "right to explanation"
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Toward Multimodal Image-to-Image Translation
- Energy-based Generative Adversarial Network
- Unrolled Generative Adversarial Networks
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
- Inverse Classification for Comparison-based Interpretability in Machine Learning
- Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
- RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal
- Learning Residual Images for Face Attribute Manipulation