mlsanityData to 7 Oct 2026

A Symbolic Approach to Explaining Bayesian Network Classifiers

arXiv 1805.03364 ↗First posted 9 May 2018cs.AI cs.LGcited by 130

Not on the map. Why?

Abstract (arXiv)

We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not) is sufficient for the classification. We consider in particular the compilation of Naive and Latent-Tree Bayesian network classifiers into Ordered Decision Diagrams (ODDs), providing a context for evaluating our proposal using case studies and experiments based on classifiers from the literature.

Key facts. Cited by 130 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 25; 2023: 26; 2024: 16; 2025: 20; 2026: 21.

130 papers.

Sort:

  1. 2021Argumentative XAI: A Surveycited by 66
  2. 2021On Explaining Random Forests with SATcited by 57
  3. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  4. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  5. 2022Logic-Based Explainability in Machine Learningcited by 47
  6. 2021Logic Explained Networkscited by 45
  7. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  8. 2022Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networkscited by 42
  9. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  10. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  11. 2021Explanations for Monotonic Classifierscited by 39
  12. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
38 more
  1. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  2. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  3. 2021Trading Complexity for Sparsity in Random Forest Explanationscited by 32
  4. 2021Provably efficient, succinct, and precise explanationscited by 32
  5. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  6. 2022Causal Explanations and XAIcited by 30
  7. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  8. 2021Foundations of Symbolic Languages for Model Interpretabilitycited by 26
  9. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  10. 2021Probabilistic Sufficient Explanationscited by 24
  11. 2023Interactive Explanations by Conflict Resolution via Argumentative Exchangescited by 24
  12. 2023Formally Explaining Neural Networks within Reactive Systemscited by 24
  13. 2022On the Computation of Necessary and Sufficient Explanationscited by 23
  14. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  15. 2022Computing Abductive Explanations for Boosted Treescited by 23
  16. 2023Logic for Explainable AIcited by 23
  17. 2023Explainability is NOT a Gamecited by 23
  18. 2024Local vs. Global Interpretability: A Computational Complexity Perspectivecited by 23
  19. 2022Feature Necessity & Relevancy in ML Classifier Explanationscited by 22
  20. 2024Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementationcited by 20
  21. 2022On Computing Probabilistic Abductive Explanationscited by 18
  22. 2023SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]cited by 18
  23. 2021On Quantifying Literals in Boolean Logic and Its Applications to Explainable AIcited by 16
  24. 2023Delivering Inflated Explanationscited by 16
  25. 2023From Robustness to Explainability and Back Againcited by 14
  26. 2021Efficient Explanations With Relevant Setscited by 12
  27. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  28. 2023On Formal Feature Attribution and Its Approximationcited by 11
  29. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 11
  30. 2023Axiomatic Aggregations of Abductive Explanationscited by 10
  31. 2025Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanationscited by 10
  32. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  33. 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guaranteescited by 10
  34. 2021Efficient Explanations for Knowledge Compilation Languagescited by 9
  35. 2022Tractable Boolean and Arithmetic Circuitscited by 9
  36. 2022Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)cited by 9
  37. 2023Anytime Approximate Formal Feature Attributioncited by 9
  38. 2021Evaluating the Correctness of Explainable AI Algorithms for Classificationcited by 8

50 most cited of 130 All 130 (JSON)