# Four Axiomatic Characterizations of the Integrated Gradients Attribution Method

arXiv: https://arxiv.org/abs/2306.13753 · HTML: https://mlsanity.com/paper/2306.13753/

## 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 (most cited first, 23 of 23)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [The Shapley Taylor Interaction Index](https://mlsanity.com/paper/1902.05622/) (2019)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [How Important Is a Neuron?](https://mlsanity.com/paper/1805.12233/) (2018)
- [Faith-Shap: The Faithful Shapley Interaction Index](https://mlsanity.com/paper/2203.00870/) (2022)
- [A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions](https://mlsanity.com/paper/2202.11912/) (2022)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)
- [Global Explanations of Neural Networks: Mapping the Landscape of Predictions](https://mlsanity.com/paper/1902.02384/) (2019)
- [Symmetry-Preserving Paths in Integrated Gradients](https://mlsanity.com/paper/2103.13533/) (2021)
- [Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability](https://mlsanity.com/paper/2305.03100/) (2023)
- [Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features](https://mlsanity.com/paper/2106.06697/) (2021)

## Built on by (most cited first, 5 of 5)

- [Attribution Methods in Asset Pricing: Do They Account for Risk?](https://mlsanity.com/paper/2407.08953/) (2024)
- [Explaining Risks: Axiomatic Risk Attributions for Financial Models](https://mlsanity.com/paper/2506.06653/) (2025)
- [Attribution Upsampling should Redistribute, Not Interpolate](https://mlsanity.com/paper/2603.16067/) (2026)
- [GRALIS: Fusing Coalition and Gradient Attribution with Closed-Form Conservation Error and Finite-Sample Guarantees](https://mlsanity.com/paper/2605.05480/) (2026)
- [Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist](https://mlsanity.com/paper/2607.14271/) (2026)

## 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.