Maximum Entropy Baseline for Integrated Gradients
Not on the map. Why?
Abstract (arXiv)
Integrated Gradients (IG), one of the most popular explainability methods available, still remains ambiguous in the selection of baseline, which may seriously impair the credibility of the explanations. This study proposes a new uniform baseline, i.e., the Maximum Entropy Baseline, which is consistent with the "uninformative" property of baselines defined in IG. In addition, we propose an improved ablating evaluation approach incorporating the new baseline, where the information conservativeness is maintained. We explain the linear transformation invariance of IG baselines from an information perspective. Finally, we assess the reliability of the explanations generated by different explainability methods and different IG baselines through extensive evaluation experiments.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 12 Apr 2022.
Builds on
23 of 32 references.
References · 23
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2013Visualizing and Understanding Convolutional Networkscited by 2,278
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
11 more
- 2019The many Shapley values for model explanationcited by 341
- 2017The (Un)reliability of saliency methodscited by 331
- 2016Top-down Neural Attention by Excitation Backpropcited by 318
- 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
- 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
- 2018PointCloud Saliency Mapscited by 112
- 2019Visualizing Deep Networks by Optimizing with Integrated Gradientscited by 59
- 2016Gradients of Counterfactualscited by 31
- 2020Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attributioncited by 19
- 2021Surrogate Model-Based Explainability Methods for Point Cloud NNscited by 18
- 2017Understanding and Comparing Deep Neural Networks for Age and Gender Classificationcited by 17
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.
3 papers.