mlsanityData to 7 Oct 2026

On Measuring Intrinsic Causal Attributions in Deep Neural Networks

arXiv 2505.09660 ↗First posted 14 May 2025stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Quantifying the causal influence of input features within neural networks has become a topic of increasing interest. Existing approaches typically assess direct, indirect, and total causal effects. This work treats NNs as structural causal models (SCMs) and extends our focus to include intrinsic causal contributions (ICC). We propose an identifiable generative post-hoc framework for quantifying ICC. We also draw a relationship between ICC and Sobol' indices. Our experiments on synthetic and real-world datasets demonstrate that ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 51 of its 90 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

51 of 90 references.

References · 51

  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. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  9. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  10. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  11. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  12. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
38 more
  1. 2019Counterfactual Visual Explanationscited by 312
  2. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
  3. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  4. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  5. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  6. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  7. 2020Multi-Objective Counterfactual Explanationscited by 157
  8. 2019Causal Discovery with Reinforcement Learningcited by 145
  9. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  10. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  11. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  12. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  13. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  14. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  15. 2020Counterfactual Data Augmentation using Locally Factored Dynamicscited by 93
  16. 2020Shapley explainability on the data manifoldcited by 88
  17. 2019Neural Network Attributions: A Causal Perspectivecited by 77
  18. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
  19. 2020Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same Endcited by 66
  20. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
  21. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  22. 2020Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactualscited by 56
  23. 2023Causal normalizing flows: from theory to practicecited by 49
  24. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  25. 2022DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal modelscited by 40
  26. 2022Indeterminacy in Generative Models: Characterization and Strong Identifiabilitycited by 33
  27. 2019Global Explanations of Neural Networks: Mapping the Landscape of Predictionscited by 32
  28. 2021Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanismscited by 20
  29. 2023Second-Order Uncertainty Quantification: Variance-Based Measurescited by 19
  30. 2018Global Model Interpretation via Recursive Partitioningcited by 17
  31. 2021Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Ratescited by 16
  32. 2022Backtracking Counterfactualscited by 15
  33. 2020Quantifying intrinsic causal contributions via structure preserving interventionscited by 12
  34. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  35. 2022Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flowscited by 9
  36. 2021Fairness seen as Global Sensitivity Analysiscited by 8
  37. 2023Towards Learning and Explaining Indirect Causal Effects in Neural Networkscited by 2
  38. 2023On Counterfactual Data Augmentation Under Confoundingcited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.