mlsanityData to 7 Oct 2026

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

arXiv 2110.08252 ↗First posted 12 Oct 2021cs.LG cs.AI cs.ITcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 12 Oct 2021.

Builds on

17 of 28 references.

References · 17

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2019Searching for MobileNetV3cited by 1,984
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  8. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  10. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  11. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  12. 2017Neural Audio Synthesis of Musical Notes with WaveNet Autoencoderscited by 222
5 more
  1. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  2. 2019RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networkscited by 126
  3. 2019A Rate-Distortion Framework for Explaining Neural Network Decisionscited by 24
  4. 2021Cartoon Explanations of Image Classifierscited by 15
  5. 2020In-Distribution Interpretability for Challenging Modalitiescited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 1; 2024: 2; 2025: 2.

11 papers.

  1. 2022Interpretable by Design: Learning Predictors by Composing Interpretable Queriescited by 26
  2. 2021RELAX: Representation Learning Explainabilitycited by 12
  3. 2022Limitations of Deep Learning for Inverse Problems on Digital Hardwarecited by 9
  4. 2022Interpretability with full complexity by constraining feature informationcited by 7
  5. 2022SHAP-XRT: The Shapley Value Meets Conditional Independence Testingcited by 6
  6. 2024FLEXtime: Filterbank learning to explain time seriescited by 6
  7. 2024Sufficient and Necessary Explanations (and What Lies in Between)cited by 3
  8. 2022The Mathematics of Artificial Intelligencecited by 0
  9. 2023On the Interplay of Subset Selection and Informed Graph Neural Networkscited by 0
  10. 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinementcited by 0
  11. 2025Direct Preference Optimization for Adaptive Concept-based Explanationscited by 0