mlsanityData to 7 Oct 2026

Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist

arXiv 2607.14271 ↗First posted 15 Jul 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Feature-attribution methods are central to explainable artificial intelligence. Their assumptions are expressed in several mathematical languages: cooperative-game values, path integrals, gradient operators, perturbation distributions, and backpropagation rules. This survey proposes a common framework for local additive feature attribution. It organizes Shapley, path-based, gradient/backpropagation, perturbation, and CAM-style methods around five specification choices: value function, reference, path, perturbation distribution, and conservation rule. It then compares these methods through an axiom-by-method matrix and links common failure modes, including baseline sensitivity, off-manifold perturbations, sanity-check failures, adversarial manipulation, and method disagreement, to the assumptions that produce them. Finally, the survey proposes a ten-item reporting checklist for studies that use local additive attributions. The central message is that attribution results are meaningful only relative to the mathematical assumptions under which they are defined, and that those assumptions should be reported.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 78 of its 111 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

78 of 111 references.

References · 78

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  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. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  10. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,097
38 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  2. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  3. 2019Attention is not Explanationcited by 916
  4. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  5. 2020Quantifying Attention Flow in Transformerscited by 759
  6. 2016The Mythos of Model Interpretabilitycited by 716
  7. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  8. 2019Attention is not not Explanationcited by 629
  9. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  10. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  11. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  12. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  13. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  14. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  15. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  16. 2017Interpretation of Neural Networks is Fragilecited by 443
  17. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  18. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  19. 2019Is Attention Interpretable?cited by 387
  20. 2019The many Shapley values for model explanationcited by 341
  21. 2017The (Un)reliability of saliency methodscited by 331
  22. 2018On the Robustness of Interpretability Methodscited by 310
  23. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  24. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  25. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  26. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  27. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  28. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  29. 2019Explanations can be manipulated and geometry is to blamecited by 215
  30. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  31. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  32. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  33. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
  34. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  35. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  36. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  37. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 156
  38. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156

50 most cited of 78 All 78 (JSON)

Built on by

Not cited yet.