mlsanityData to 14 Oct 2026

A Functional Information Perspective on Model Interpretation

arXiv 2206.05700 ↗First posted 12 Jun 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input. We rely on the log-Sobolev inequality that bounds the functional entropy by the functional Fisher information with respect to the covariance of the data. This provides a principled way to measure the amount of information contribution of a subset of features to the decision function. Through extensive experiments, we show that our method surpasses existing interpretability sampling-based methods on various data signals such as image, text, and audio.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  9. 2018Sanity Checks for Saliency Mapscited by 1,156
  10. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  11. 2016End to End Learning for Self-Driving Carscited by 1,009
  12. 2014Striving for Simplicity: The All Convolutional Netcited by 990
17 more
  1. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  2. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  3. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  4. 2015Recent Advances in Convolutional Neural Networkscited by 360
  5. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 297
  6. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  7. 2020A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promisescited by 231
  8. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  9. 2015A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classificationcited by 92
  10. 2016Very Deep Convolutional Neural Networks for Raw Waveformscited by 68
  11. 2018A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationscited by 60
  12. 2020Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropiescited by 57
  13. 2020TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aidscited by 42
  14. 2020Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorizationcited by 23
  15. 2021Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventionscited by 15
  16. 2021Latent Space Explanation by Interventioncited by 13
  17. 2016Learning a Metric Embedding for Face Recognition using the Multibatch Methodcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1.

5 papers.

  1. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  2. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  3. 2023Layer Collaboration in the Forward-Forward Algorithmcited by 21
  4. 2022An Additive Instance-Wise Approach to Multi-class Model Interpretationcited by 3
  5. 2023BELLA: Black box model Explanations by Local Linear Approximationscited by 0