Explainable AI using expressive Boolean formulas
arXiv:2306.03976 · doi:10.3390/make5040086
Abstract
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.
arXiv comment28 pages, 16 figures, 4 tables
References in corpus (13)
- Scikit-learn: Machine Learning in Python
- The Variational Quantum Eigensolver: a review of methods and best practices
- A Survey on the Explainability of Supervised Machine Learning
- Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
- Perspectives of quantum annealing: Methods and implementations
- Physics-Inspired Optimization for Quadratic Unconstrained Problems Using a Digital Annealer
- Supersparse Linear Integer Models for Optimized Medical Scoring Systems
- Quantum Metropolis Sampling
- Survey and Benchmarking of Machine Learning Accelerators
- Compilation of Fault-Tolerant Quantum Heuristics for Combinatorial Optimization
- Quantum speedup of branch-and-bound algorithms
- MLIC: A MaxSAT-Based framework for learning interpretable classification rules
- IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules