mlsanityData to 14 Oct 2026

Explainable AI using expressive Boolean formulas

arXiv 2306.03976 ↗First posted 6 Jun 2023cs.AI cs.LG math.OCcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose and implement an interpretable machine learning classification model for Explainable AI (XAI) based on expressive Boolean formulas. Potential applications include credit scoring and diagnosis of medical conditions. The Boolean formula defines a rule with tunable complexity (or interpretability), according to which input data are classified. Such a formula can include any operator that can be applied to one or more Boolean variables, thus providing higher expressivity compared to more rigid rule-based and tree-based approaches. The classifier is trained using native local optimization techniques, efficiently searching the space of feasible formulas. Shallow rules can be determined by fast Integer Linear Programming (ILP) or Quadratic Unconstrained Binary Optimization (QUBO) solvers, potentially powered by special purpose hardware or quantum devices. We combine the expressivity and efficiency of the native local optimizer with the fast operation of these devices by executing non-local moves that optimize over subtrees of the full Boolean formula. We provide extensive numerical benchmarking results featuring several baselines on well-known public datasets. Based on the results, we find that the native local rule classifier is generally competitive with the other classifiers. The addition of non-local moves achieves similar results with fewer iterations, and therefore using specialized or quantum hardware could lead to a speedup by fast proposal of non-local moves.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 66 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

18 of 66 references.

References · 18

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  4. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  5. 2020A Survey on the Explainability of Supervised Machine Learningcited by 227
  6. 2015Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction modelcited by 140
  7. 2015Supersparse Linear Integer Models for Optimized Medical Scoring Systemscited by 76
  8. 2014Falling Rule Listscited by 59
  9. 2017Learning Certifiably Optimal Rule Lists for Categorical Datacited by 50
  10. 2020Robust and Stable Black Box Explanationscited by 47
  11. 2017Interpreting Blackbox Models via Model Extractioncited by 44
  12. 2015Learning Optimized Or's of And'scited by 14
6 more
  1. 2018MLIC: A MaxSAT-Based framework for learning interpretable classification rulescited by 14
  2. 2015Interpretable Two-level Boolean Rule Learning for Classificationcited by 10
  3. 2021Interpretable and Fair Boolean Rule Sets via Column Generationcited by 10
  4. 2020IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rulescited by 8
  5. 2019Quantum speedup of branch-and-bound algorithmscited by 1
  6. 2021Mixed-Integer Programming Using a Bosonic Quantum Computercited by 1

Built on by

Cited by year

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

2 papers.

  1. 2023Boolformer: Symbolic Regression of Logic Functions with Transformerscited by 5
  2. 2024Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importancecited by 3