paper-with-me

Papers

Maximum Entropy Baseline for Integrated Gradients

2022-04-12 · Hanxiao Tan

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.

📄 PDF Abstract BibTeX arXiv:2204.05948

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry

2026-05-07 · Gabriele Martino, Sebastian Tschiatschek arxiv

Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We…

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

2026-03-13 · Jun Xue, Junze Wang, Shanze Wang, Xinming Zhang 외 arxiv

Scaling Maximum Entropy Reinforcement Learning (RL) to high-dimensional humanoid control remains a fundamental challenge, as the ''curse of dimensionality'' induces severe exploration inefficiency and training instabilit…

Reinforcement LearningContinuous Control

Exploring unfairness in Integrated Gradients based attribution methods

2021-09-29 · David Drakard, Rosanne Liu, Jason Yosinski

Numerous methods have attempted to explain and interpret predictions made by machine learning models in terms of their inputs. Known as “attribution methods” they notably include the Integrated Gradi…

Fairness

Implicit Policy for Reinforcement Learning

2018-06-10 · Yunhao Tang, Shipra Agrawal

We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gra…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Compensated Integrated Gradients to Reliably Interpret EEG Classification

2018-11-21 · Kazuki Tachikawa, Yuji Kawai, Jihoon Park, Minoru Asada

Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction. This method, however, requires an appropriat…

ClassificationEEGElectroencephalogram (EEG)General Classification