# Explaining Deep Learning Models using Causal Inference

arXiv: https://arxiv.org/abs/1811.04376 · HTML: https://mlsanity.com/paper/1811.04376/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2018.

## Built on by (most cited first, 18 of 18)

- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [Evaluation Methods and Measures for Causal Learning Algorithms](https://mlsanity.com/paper/2202.02896/) (2022)
- [Deep Causal Learning: Representation, Discovery and Inference](https://mlsanity.com/paper/2211.03374/) (2022)
- [Causality Analysis for Evaluating the Security of Large Language Models](https://mlsanity.com/paper/2312.07876/) (2023)
- [Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation](https://mlsanity.com/paper/2109.04518/) (2021)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective](https://mlsanity.com/paper/2303.00244/) (2023)
- [Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models](https://mlsanity.com/paper/2512.19297/) (2025)
- [CausAdv: A Causal-based Framework for Detecting Adversarial Examples](https://mlsanity.com/paper/2411.00839/) (2024)
- [Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations](https://mlsanity.com/paper/2405.20672/) (2024)
- [ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering](https://mlsanity.com/paper/2508.21010/) (2025)
- [On Causal Inference for Data-free Structured Pruning](https://mlsanity.com/paper/2112.10229/) (2021)
- [Causality-Driven Neural Network Repair: Challenges and Opportunities](https://mlsanity.com/paper/2504.17946/) (2025)

## Abstract (arXiv)

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models. In this work, we use ideas from causal inference to describe a general framework to reason over CNN models. Specifically, we build a Structural Causal Model (SCM) as an abstraction over a specific aspect of the CNN. We also formulate a method to quantitatively rank the filters of a convolution layer according to their counterfactual importance. We illustrate our approach with popular CNN architectures such as LeNet5, VGG19, and ResNet32.