mlsanityData to 14 Oct 2026

Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

arXiv 1802.07814 ↗First posted 21 Feb 2018cs.LG cs.AI stat.MLcited by 248

Not on the map. Why?

Abstract (arXiv)

We introduce instancewise feature selection as a methodology for model interpretation. Our method is based on learning a function to extract a subset of features that are most informative for each given example. This feature selector is trained to maximize the mutual information between selected features and the response variable, where the conditional distribution of the response variable given the input is the model to be explained. We develop an efficient variational approximation to the mutual information, and show the effectiveness of our method on a variety of synthetic and real data sets using both quantitative metrics and human evaluation.

Key facts. Cited by 248 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 50; 2022: 58; 2023: 53; 2024: 34; 2025: 37; 2026: 16.

248 papers.

Sort:

By area:

  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  2. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  3. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  4. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
  5. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 138
  6. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  7. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  8. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 125
  9. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 115
  10. 2021Implicit MLE: Backpropagating Through Discrete Exponential Family Distributionscited by 98
  11. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  12. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
38 more
  1. 2021Explaining Time Series Predictions with Dynamic Maskscited by 73
  2. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  3. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  4. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  5. 2023Learning to Maximize Mutual Information for Dynamic Feature Selectioncited by 56
  6. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  7. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 50
  8. 2021Explainable Artificial Intelligence Approaches: A Surveycited by 40
  9. 2022On the Explainability of Natural Language Processing Deep Modelscited by 38
  10. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  11. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  12. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  13. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  14. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  15. 2023Trompt: Towards a Better Deep Neural Network for Tabular Datacited by 36
  16. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  17. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
  18. 2021Locally Sparse Neural Networks for Tabular Biomedical Datacited by 34
  19. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
  20. 2022SIMPLE: A Gradient Estimator for k-Subset Samplingcited by 34
  21. 2021Local Interpretations for Explainable Natural Language Processing: A Surveycited by 31
  22. 2021Toward Explainable AI for Regression Modelscited by 31
  23. 2022Backpropagation through Combinatorial Algorithms: Identity with Projection Workscited by 29
  24. 2022The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizationscited by 29
  25. 2021Counterfactual Explanations for Neural Recommenderscited by 27
  26. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  27. 2023Circuit Breaking: Removing Model Behaviors with Targeted Ablationcited by 27
  28. 2021Rationales for Sequential Predictionscited by 26
  29. 2024Optimal ablation for interpretabilitycited by 25
  30. 2023Self-Interpretable Time Series Prediction with Counterfactual Explanationscited by 24
  31. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  32. 2022OmniXAI: A Library for Explainable AIcited by 21
  33. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 21
  34. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  35. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
  36. 2023CoRTX: Contrastive Framework for Real-time Explanationcited by 20
  37. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  38. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19

50 most cited of 248 All 248 (JSON)