# Fast Real-time Counterfactual Explanations

arXiv: https://arxiv.org/abs/2007.05684 · HTML: https://mlsanity.com/paper/2007.05684/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks](https://mlsanity.com/paper/2104.08060/) (2021)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations](https://mlsanity.com/paper/2302.12689/) (2023)
- [Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network](https://mlsanity.com/paper/2110.14927/) (2021)
- [Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifiers](https://mlsanity.com/paper/2405.05295/) (2024)
- [TACE: Tumor-Aware Counterfactual Explanations](https://mlsanity.com/paper/2409.13045/) (2024)
- [Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints](https://mlsanity.com/paper/2511.20236/) (2025)

## Abstract (arXiv)

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.