mlsanityData to 7 Oct 2026

Neural Network Attributions: A Causal Perspective

arXiv 1902.02302 ↗First posted 6 Feb 2019cs.LG stat.MLcited by 77

Not on the map. Why?

Abstract (arXiv)

We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such). The neural network architecture is viewed as a Structural Causal Model, and a methodology to compute the causal effect of each feature on the output is presented. With reasonable assumptions on the causal structure of the input data, we propose algorithms to efficiently compute the causal effects, as well as scale the approach to data with large dimensionality. We also show how this method can be used for recurrent neural networks. We report experimental results on both simulated and real datasets showcasing the promise and usefulness of the proposed algorithm.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 14; 2023: 18; 2024: 7; 2025: 12; 2026: 7.

77 papers.

Sort:

By area:

  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  3. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  4. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  5. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  6. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  7. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  8. 2022A Causal Lens for Controllable Text Generationcited by 45
  9. 2022Causality-based Neural Network Repaircited by 44
  10. 2023Rigorously Assessing Natural Language Explanations of Neuronscited by 44
  11. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  12. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
38 more
  1. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  2. 2024Causal Concept Graph Models: Beyond Causal Opacity in Deep Learningcited by 28
  3. 2023Variational Information Pursuit for Interpretable Predictionscited by 25
  4. 2021On Causally Disentangled Representationscited by 22
  5. 2021Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanismscited by 20
  6. 2022Adaptive Fairness Improvement Based on Causality Analysiscited by 17
  7. 2023Interpretation of Time-Series Deep Models: A Surveycited by 15
  8. 2025Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associationscited by 14
  9. 2024LLMScan: Causal Scan for LLM Misbehavior Detectioncited by 13
  10. 2026CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attributioncited by 13
  11. 2022On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approachcited by 11
  12. 2021Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?cited by 10
  13. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  14. 2025Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetycited by 10
  15. 2023Causality Analysis for Evaluating the Security of Large Language Modelscited by 9
  16. 2023Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Predictioncited by 9
  17. 2021Instance-wise Causal Feature Selection for Model Interpretationcited by 8
  18. 2021Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systemscited by 8
  19. 2023Causal Analysis for Robust Interpretability of Neural Networkscited by 8
  20. 2021Causal Learning for Socially Responsible AIcited by 7
  21. 2022Quality issues in Machine Learning Software Systemscited by 7
  22. 2021Improving Attribution Methods by Learning Submodular Functionscited by 5
  23. 2021Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?cited by 5
  24. 2022Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forestcited by 5
  25. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  26. 2023SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspectivecited by 5
  27. 2024DiConStruct: Causal Concept-based Explanations through Black-Box Distillationcited by 5
  28. 2023Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generationcited by 4
  29. 2023How Generalizable are Deepfake Image Detectors? An Empirical Studycited by 3
  30. 2023Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiescited by 3
  31. 2025Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Modelscited by 3
  32. 2021Did I do that? Blame as a means to identify controlled effects in reinforcement learningcited by 2
  33. 2021DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Trainingcited by 2
  34. 2023Towards Learning and Explaining Indirect Causal Effects in Neural Networkscited by 2
  35. 2023On the Multiple Roles of Ontologies in Explainable AIcited by 2
  36. 2024Causal Feature Selection for Responsible Machine Learningcited by 2
  37. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  38. 2026Causal Attribution via Activation Patchingcited by 2

50 most cited of 77 All 77 (JSON)