# Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation

arXiv: https://arxiv.org/abs/2101.06930 · HTML: https://mlsanity.com/paper/2101.06930/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 18 Jan 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Yelp Dataset Challenge: Review Rating Prediction](https://mlsanity.com/paper/1605.05362/) (2016)
- [Explanation by Progressive Exaggeration](https://mlsanity.com/paper/1911.00483/) (2019)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [Measurable Counterfactual Local Explanations for Any Classifier](https://mlsanity.com/paper/1908.03020/) (2019)
- [Generative Counterfactual Introspection for Explainable Deep Learning](https://mlsanity.com/paper/1907.03077/) (2019)
- [xGEMs: Generating Examplars to Explain Black-Box Models](https://mlsanity.com/paper/1806.08867/) (2018)
- [Explaining Deep Learning Models with Constrained Adversarial Examples](https://mlsanity.com/paper/1906.10671/) (2019)
- [Should Adversarial Attacks Use Pixel p-Norm?](https://mlsanity.com/paper/1906.02439/) (2019)

## Built on by (most cited first, 11 of 11)

- [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)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Counterfactual Explanations for Models of Code](https://mlsanity.com/paper/2111.05711/) (2021)
- [Model-Based Counterfactual Synthesizer for Interpretation](https://mlsanity.com/paper/2106.08971/) (2021)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Differentially Private Counterfactuals via Functional Mechanism](https://mlsanity.com/paper/2208.02878/) (2022)
- [On the Importance of Domain-specific Explanations in AI-based Cybersecurity Systems (Technical Report)](https://mlsanity.com/paper/2108.02006/) (2021)
- [SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems](https://mlsanity.com/paper/2307.15786/) (2023)
- [Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space](https://mlsanity.com/paper/2207.07710/) (2022)
- [A General Search-based Framework for Generating Textual Counterfactual Explanations](https://mlsanity.com/paper/2211.00369/) (2022)
- [On Modifying a Neural Network's Perception](https://mlsanity.com/paper/2303.02655/) (2023)

## Abstract (arXiv)

With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios. Current interpretation techniques mainly focus on the feature attribution perspective, which are limited in indicating why and how particular explanations are related to the prediction. To this end, an intriguing class of explanations, named counterfactuals, has been developed to further explore the "what-if" circumstances for interpretation, and enables the reasoning capability on black-box models. However, generating counterfactuals for raw data instances (i.e., text and image) is still in the early stage due to its challenges on high data dimensionality and unsemantic raw features. In this paper, we design a framework to generate counterfactuals specifically for raw data instances with the proposed Attribute-Informed Perturbation (AIP). By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Instead of directly modifying instances in the data space, we iteratively optimize the constructed attribute-informed latent space, where features are more robust and semantic. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework, and show the superiority over other alternatives. Besides, we also introduce some practical applications based on our framework, indicating its potential beyond the model interpretability aspect.