mlsanityData to 7 Oct 2026

Interpretability via Model Extraction

arXiv 1706.09773 ↗First posted 29 Jun 2017cs.LG cs.CY stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable model; as long as the approximation quality is good, then statistical properties of the complex model are reflected in the interpretable model. We show how model extraction can be used to understand and debug random forests and neural nets trained on several datasets from the UCI Machine Learning Repository, as well as control policies learned for several classical reinforcement learning problems.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 10; 2024: 3; 2025: 5; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  2. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  3. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  4. 2022Neural Basis Models for Interpretabilitycited by 56
  5. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  6. 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
  7. 2022Logic-Based Explainability in Machine Learningcited by 47
  8. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  9. 2021Provably efficient, succinct, and precise explanationscited by 32
  10. 2021M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysiscited by 29
  11. 2021The Role of Explainability in Assuring Safety of Machine Learning in Healthcarecited by 26
  12. 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
28 more
  1. 2023Dual Student Networks for Data-Free Model Stealingcited by 17
  2. 2022From Black Boxes to Conversations: Incorporating XAI in a Conversational Agentcited by 14
  3. 2024Towards a theory of model distillationcited by 14
  4. 2022A Human-Centric Take on Model Monitoringcited by 9
  5. 2022Superpolynomial Lower Bounds for Decision Tree Learning and Testingcited by 9
  6. 2022A Query-Optimal Algorithm for Finding Counterfactualscited by 7
  7. 2024A Theory of Interpretable Approximationscited by 7
  8. 2021Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifierscited by 6
  9. 2022Trade-off Between Efficiency and Consistency for Removal-based Explanationscited by 6
  10. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  11. 2023Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspectscited by 5
  12. 2023Properly Learning Decision Trees with Queries Is NP-Hardcited by 5
  13. 2025Model-Agnostic Policy Explanations with Large Language Modelscited by 4
  14. 2023Explaining Agent Behavior with Large Language Modelscited by 3
  15. 2023Understanding Your Agent: Leveraging Large Language Models for Behavior Explanationcited by 3
  16. 2023i-Align: an interpretable knowledge graph alignment modelcited by 2
  17. 2026Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretationcited by 2
  18. 2022(When) Are Contrastive Explanations of Reinforcement Learning Helpful?cited by 1
  19. 2023Interpretable Differencing of Machine Learning Modelscited by 1
  20. 2023Responsible Emergent Multi-Agent Behaviorcited by 1
  21. 2024Aligning XAI with EU Regulations for Smart Biomedical Devices: A Methodology for Compliance Analysiscited by 1
  22. 2025Models That Are Interpretable But Not Transparentcited by 1
  23. 2025Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Userscited by 1
  24. 2025Explainable AI the Latest Advancements and New Trendscited by 1
  25. 2021BODAME: Bilevel Optimization for Defense Against Model Extractioncited by 0
  26. 2021Forward Composition Propagation for Explainable Neural Reasoningcited by 0
  27. 2023ViT-Calibrator: Decision Stream Calibration for Vision Transformercited by 0
  28. 2026Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanismscited by 0