mlsanityData to 14 Oct 2026

Computing Abductive Explanations for Boosted Trees

arXiv 2209.07740 ↗First posted 16 Sep 2022cs.AI cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Boosted trees is a dominant ML model, exhibiting high accuracy. However, boosted trees are hardly intelligible, and this is a problem whenever they are used in safety-critical applications. Indeed, in such a context, rigorous explanations of the predictions made are expected. Recent work have shown how subset-minimal abductive explanations can be derived for boosted trees, using automated reasoning techniques. However, the generation of such well-founded explanations is intractable in the general case. To improve the scalability of their generation, we introduce the notion of tree-specific explanation for a boosted tree. We show that tree-specific explanations are abductive explanations that can be computed in polynomial time. We also explain how to derive a subset-minimal abductive explanation from a tree-specific explanation. Experiments on various datasets show the computational benefits of leveraging tree-specific explanations for deriving subset-minimal abductive explanations.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

30 of 52 references.

References · 30

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  5. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  6. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  8. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  9. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  10. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  11. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  12. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
18 more
  1. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  2. 2020On The Reasons Behind Decisionscited by 100
  3. 2017Verifying Properties of Binarized Deep Neural Networkscited by 79
  4. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  5. 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 72
  6. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  7. 2014Falling Rule Listscited by 59
  8. 2021On Explaining Random Forests with SATcited by 57
  9. 2020On Explaining Decision Treescited by 49
  10. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  11. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  12. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  13. 2021Optimal Counterfactual Explanations in Tree Ensemblescited by 36
  14. 2019On Validating, Repairing and Refining Heuristic ML Explanationscited by 32
  15. 2021Trading Complexity for Sparsity in Random Forest Explanationscited by 32
  16. 2020On Symbolically Encoding the Behavior of Random Forestscited by 15
  17. 2020On Relating 'Why?' and 'Why Not?' Explanationscited by 15
  18. 2019Regional Tree Regularization for Interpretability in Black Box Modelscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 7; 2026: 8.

23 papers.

Sort:

By area:

  1. 2023Logic for Explainable AIcited by 23
  2. 2024Local vs. Global Interpretability: A Computational Complexity Perspectivecited by 23
  3. 2025Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanationscited by 13
  4. 2024Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretationcited by 11
  5. 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guaranteescited by 11
  6. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  7. 2024Abductive explanations of classifiers under constraints: Complexity and propertiescited by 7
  8. 2024Axiomatic Characterisations of Sample-based Explainerscited by 3
  9. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  10. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  11. 2026Unifying Formal Explanations: A Complexity-Theoretic Perspectivecited by 2
  12. 2023Finding Minimum-Cost Explanations for Predictions made by Tree Ensemblescited by 1
11 more
  1. 2025Feature Relevancy, Necessity and Usefulness: Complexity and Algorithmscited by 1
  2. 2025Uncovering Bugs in Formal Explainers: A Case Study with PyXAIcited by 1
  3. 2026Provably Explaining Neural Additive Modelscited by 1
  4. 2026Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networkscited by 1
  5. 2025Comparing Neural Network Encodings for Logic-based Explainabilitycited by 0
  6. 2025Efficient & Correct Predictive Equivalence for Decision Treescited by 0
  7. 2025A Rectification-Based Approach for Distilling Boosted Trees into Decision Treescited by 0
  8. 2026Formally Explaining Decision Tree Models with Answer Set Programmingcited by 0
  9. 2026Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Optioncited by 0
  10. 2026Rigorous Explanations for Tree Ensemblescited by 0
  11. 2026Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Modelscited by 0