mlsanityData to 7 Oct 2026

Towards Learning and Explaining Indirect Causal Effects in Neural Networks

arXiv 2303.13850 ↗First posted 24 Mar 2023cs.LG cs.AI stat.MEcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider only direct and total causal effects assuming independence among input variables. We view an NN as a structural causal model (SCM) and extend our focus to include indirect causal effects by introducing feedforward connections among input neurons. We propose an ante-hoc method that captures and maintains direct, indirect, and total causal effects during NN model training. We also propose an algorithm for quantifying learned causal effects in an NN model and efficient approximation strategies for quantifying causal effects in high-dimensional data. Extensive experiments conducted on synthetic and real-world datasets demonstrate that the causal effects learned by our ante-hoc method better approximate the ground truth effects compared to existing methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

45 of 58 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  11. 2020Concept Bottleneck Modelscited by 1,022
  12. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
33 more
  1. 2019Counterfactual Visual Explanationscited by 312
  2. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  3. 2013Direct and Indirect Effectscited by 276
  4. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  5. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  6. 2019Recurrent Independent Mechanismscited by 219
  7. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  8. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  9. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  10. 2016Grad-CAM: Why did you say that?cited by 159
  11. 2020Multi-Objective Counterfactual Explanationscited by 157
  12. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  13. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  14. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  15. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  16. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  17. 2017Learning Independent Causal Mechanismscited by 104
  18. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  19. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  20. 2018Grounding Visual Explanationscited by 92
  21. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  22. 2019Neural Network Attributions: A Causal Perspectivecited by 77
  23. 2020Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same Endcited by 66
  24. 2020Treatment effect estimation with disentangled latent factorscited by 63
  25. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  26. 2020Generative causal explanations of black-box classifierscited by 41
  27. 2020CASTLE: Regularization via Auxiliary Causal Graph Discoverycited by 41
  28. 2022LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Modelscited by 28
  29. 2019Causal Regularizationcited by 21
  30. 2021Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanismscited by 20
  31. 2021Comprehensible Convolutional Neural Networks via Guided Concept Learningcited by 11
  32. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  33. 2020A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attributioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Modelscited by 1
  2. 2025On Measuring Intrinsic Causal Attributions in Deep Neural Networkscited by 0