# Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach

arXiv: https://arxiv.org/abs/2409.16429 · HTML: https://mlsanity.com/paper/2409.16429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [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)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Visualizing Deep Neural Network Decisions: Prediction Difference Analysis](https://mlsanity.com/paper/1702.04595/) (2017)
- [XRAI: Better Attributions Through Regions](https://mlsanity.com/paper/1906.02825/) (2019)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [Attribution in Scale and Space](https://mlsanity.com/paper/2004.03383/) (2020)
- [Review of Visual Saliency Detection with Comprehensive Information](https://mlsanity.com/paper/1803.03391/) (2018)
- [Visualizing Deep Networks by Optimizing with Integrated Gradients](https://mlsanity.com/paper/1905.00954/) (2019)
- [Graph Neural Network Explanations are Fragile](https://mlsanity.com/paper/2406.03193/) (2024)
- [IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients](https://mlsanity.com/paper/2303.14242/) (2023)
- [Graph Neural Network Causal Explanation via Neural Causal Models](https://mlsanity.com/paper/2407.09378/) (2024)
- [Study of Workload Interference with Intelligent Routing on Dragonfly](https://mlsanity.com/paper/2403.16288/) (2024)

## Abstract (arXiv)

Numerous explanation methods have been recently developed to interpret the decisions made by deep neural network (DNN) models. For image classifiers, these methods typically provide an attribution score to each pixel in the image to quantify its contribution to the prediction. However, most of these explanation methods appropriate attribution scores to pixels independently, even though both humans and DNNs make decisions by analyzing a set of closely related pixels simultaneously. Hence, the attribution score of a pixel should be evaluated jointly by considering itself and its structurally-similar pixels. We propose a method called IProp, which models each pixel's individual attribution score as a source of explanatory information and explains the image prediction through the dynamic propagation of information across all pixels. To formulate the information propagation, IProp adopts the Markov Reward Process, which guarantees convergence, and the final status indicates the desired pixels' attribution scores. Furthermore, IProp is compatible with any existing attribution-based explanation method. Extensive experiments on various explanation methods and DNN models verify that IProp significantly improves them on a variety of interpretability metrics.