Fast Real-time Counterfactual Explanations

Abstract

Counterfactual explanations are considered, which is to answer {\it why the prediction is class A but not B.} Different from previous optimization based methods, an optimization-free Fast ReAl-time Counterfactual Explanation (FRACE) algorithm is proposed benefiting from the development of multi-domain image to image translation algorithms. Built from starGAN, a transformer is trained as a residual generator conditional on a classifier constrained under a proposal perturbation loss which maintains the content information of the query image, but just the class-specific semantic information is changed. The transformer can transfer the query image to any counterfactual class, and during inference, our explanation can be generated by it only within a forward time. It is fast and can satisfy the real-time practical application. Because of the adversarial training of GAN, our explanation is also more realistic compared to other counterparts. The experimental results demonstrate that our proposal is better than the existing state of the art in terms of quality and speed.

This paper has been accepted by ICML workshop 2020

References in corpus (9)

• Conditional Generative Adversarial Nets
• Axiomatic Attribution for Deep Networks
• Learning Important Features Through Propagating Activation Differences
• Conditional Image Synthesis With Auxiliary Classifier GANs
• EMNIST: an extension of MNIST to handwritten letters
• Generating Adversarial Examples with Adversarial Networks
• An Overview of Machine Teaching
• Counterfactual Visual Explanations
• IDK Cascades: Fast Deep Learning by Learning not to Overthink

Cited by in corpus (2)

• GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects