# A Rate-Distortion Framework for Explaining Black-box Model Decisions

arXiv: https://arxiv.org/abs/2110.08252 · HTML: https://mlsanity.com/paper/2110.08252/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 12 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [A Rate-Distortion Framework for Explaining Neural Network Decisions](https://mlsanity.com/paper/1905.11092/) (2019)
- [Cartoon Explanations of Image Classifiers](https://mlsanity.com/paper/2110.03485/) (2021)
- [In-Distribution Interpretability for Challenging Modalities](https://mlsanity.com/paper/2007.00758/) (2020)

## Built on by (most cited first, 11 of 11)

- [Interpretable by Design: Learning Predictors by Composing Interpretable Queries](https://mlsanity.com/paper/2207.00938/) (2022)
- [RELAX: Representation Learning Explainability](https://mlsanity.com/paper/2112.10161/) (2021)
- [Limitations of Deep Learning for Inverse Problems on Digital Hardware](https://mlsanity.com/paper/2202.13490/) (2022)
- [Interpretability with full complexity by constraining feature information](https://mlsanity.com/paper/2211.17264/) (2022)
- [SHAP-XRT: The Shapley Value Meets Conditional Independence Testing](https://mlsanity.com/paper/2207.07038/) (2022)
- [FLEXtime: Filterbank learning to explain time series](https://mlsanity.com/paper/2411.05841/) (2024)
- [Sufficient and Necessary Explanations (and What Lies in Between)](https://mlsanity.com/paper/2409.20427/) (2024)
- [The Mathematics of Artificial Intelligence](https://mlsanity.com/paper/2203.08890/) (2022)
- [On the Interplay of Subset Selection and Informed Graph Neural Networks](https://mlsanity.com/paper/2306.10066/) (2023)
- [Enhancing Performance of Explainable AI Models with Constrained Concept Refinement](https://mlsanity.com/paper/2502.06775/) (2025)
- [Direct Preference Optimization for Adaptive Concept-based Explanations](https://mlsanity.com/paper/2505.15626/) (2025)

## Abstract (arXiv)

We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations of the target input signal and applies to any differentiable pre-trained model such as neural networks. Our experiments demonstrate the framework's adaptability to diverse data modalities, particularly images, audio, and physical simulations of urban environments.