mlsanityData to 14 Oct 2026

Four Axiomatic Characterizations of the Integrated Gradients Attribution Method

arXiv 2306.13753 ↗First posted 23 Jun 2023cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have produced significant progress among machine learning models in terms of accuracy and functionality, but their inner workings are still largely unknown. Attribution methods seek to shine a light on these "black box" models by indicating how much each input contributed to a model's outputs. The Integrated Gradients (IG) method is a state of the art baseline attribution method in the axiomatic vein, meaning it is designed to conform to particular principles of attributions. We present four axiomatic characterizations of IG, establishing IG as the unique method to satisfy different sets of axioms among a class of attribution methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 23 of its 46 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

23 of 46 references.

References · 23

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  7. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  9. 2019The many Shapley values for model explanationcited by 344
  10. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  11. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 199
  12. 2019The Shapley Taylor Interaction Indexcited by 143
11 more
  1. 2015Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction modelcited by 140
  2. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  3. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  4. 2018How Important Is a Neuron?cited by 73
  5. 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 69
  6. 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
  7. 2020Attribution in Scale and Spacecited by 61
  8. 2019Global Explanations of Neural Networks: Mapping the Landscape of Predictionscited by 32
  9. 2021Symmetry-Preserving Paths in Integrated Gradientscited by 4
  10. 2023Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainabilitycited by 2
  11. 2021Explaining the Deep Natural Language Processing by Mining Textual Interpretable Featurescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Attribution Methods in Asset Pricing: Do They Account for Risk?cited by 1
  2. 2025Explaining Risks: Axiomatic Risk Attributions for Financial Modelscited by 0
  3. 2026Attribution Upsampling should Redistribute, Not Interpolatecited by 0
  4. 2026GRALIS: Fusing Coalition and Gradient Attribution with Closed-Form Conservation Error and Finite-Sample Guaranteescited by 0
  5. 2026Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklistcited by 0