mlsanityData to 14 Oct 2026

Explaining Deep Learning Models using Causal Inference

arXiv 1811.04376 ↗First posted 11 Nov 2018cs.LG cs.AI stat.MLcited by 18

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 4; 2023: 3; 2024: 2; 2025: 3.

18 papers.

Sort:

By area:

  1. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 205
  2. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  3. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  4. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  5. 2022Causality-based Neural Network Repaircited by 47
  6. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  7. 2022Evaluation Methods and Measures for Causal Learning Algorithmscited by 23
  8. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  9. 2023Causality Analysis for Evaluating the Security of Large Language Modelscited by 11
  10. 2021Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanationcited by 8
  11. 2021Causal Learning for Socially Responsible AIcited by 7
  12. 2023SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspectivecited by 5
6 more
  1. 2025Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Modelscited by 3
  2. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examplescited by 2
  3. 2024Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbationscited by 1
  4. 2025ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answeringcited by 1
  5. 2021On Causal Inference for Data-free Structured Pruningcited by 0
  6. 2025Causality-Driven Neural Network Repair: Challenges and Opportunitiescited by 0