# Generative causal explanations of black-box classifiers

arXiv: https://arxiv.org/abs/2006.13913 · HTML: https://mlsanity.com/paper/2006.13913/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 30 of 41)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms](https://mlsanity.com/paper/2108.00783/) (2021)
- [FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods](https://mlsanity.com/paper/2308.06248/) (2023)
- [Towards LLM-guided Causal Explainability for Black-box Text Classifiers](https://mlsanity.com/paper/2309.13340/) (2023)
- [Learning to Receive Help: Intervention-Aware Concept Embedding Models](https://mlsanity.com/paper/2309.16928/) (2023)
- [Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis](https://mlsanity.com/paper/2202.07728/) (2022)
- [OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks](https://mlsanity.com/paper/2203.15209/) (2022)
- [Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey](https://mlsanity.com/paper/2108.09003/) (2021)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Causal Evaluation of Language Models](https://mlsanity.com/paper/2405.00622/) (2024)
- [CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis](https://mlsanity.com/paper/2301.01642/) (2023)
- [Cartoon Explanations of Image Classifiers](https://mlsanity.com/paper/2110.03485/) (2021)
- [Core Risk Minimization using Salient ImageNet](https://mlsanity.com/paper/2203.15566/) (2022)
- [Explainable Artificial Intelligence for Medical Applications: A Review](https://mlsanity.com/paper/2412.01829/) (2024)
- [medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space](https://mlsanity.com/paper/2204.05376/) (2022)
- [Instance-wise Causal Feature Selection for Model Interpretation](https://mlsanity.com/paper/2104.12759/) (2021)
- [Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation](https://mlsanity.com/paper/2109.04518/) (2021)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)
- [DiConStruct: Causal Concept-based Explanations through Black-Box Distillation](https://mlsanity.com/paper/2401.08534/) (2024)
- [Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces](https://mlsanity.com/paper/2206.05257/) (2022)
- [GLANCE: Global to Local Architecture-Neutral Concept-based Explanations](https://mlsanity.com/paper/2207.01917/) (2022)
- [Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs](https://mlsanity.com/paper/2305.18362/) (2023)
- [Causal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset](https://mlsanity.com/paper/2401.11394/) (2024)
- [Data-Centric Debugging: mitigating model failures via targeted data collection](https://mlsanity.com/paper/2211.09859/) (2022)
- [On Pitfalls of textitRemOve-And-Retrain: Data Processing Inequality Perspective](https://mlsanity.com/paper/2304.13836/) (2023)
- [Towards Learning and Explaining Indirect Causal Effects in Neural Networks](https://mlsanity.com/paper/2303.13850/) (2023)

## Abstract (arXiv)

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a change in the classifier output statistics. To construct these explanations, we design a learning framework that leverages a generative model and information-theoretic measures of causal influence. Our objective function encourages both the generative model to faithfully represent the data distribution and the latent factors to have a large causal influence on the classifier output. Our method learns both global and local explanations, is compatible with any classifier that admits class probabilities and a gradient, and does not require labeled attributes or knowledge of causal structure. Using carefully controlled test cases, we provide intuition that illuminates the function of our objective. We then demonstrate the practical utility of our method on image recognition tasks.