White-box Induction From SVM Models: Explainable AI with Logic Programming

TL;DR

This paper introduces a novel method for extracting logical explanations from SVM models by leveraging support vectors and SHAP, improving over traditional ILP algorithms in interpretability and performance.

Contribution

The proposed approach combines SVMs, SHAP, and ILP to produce globally optimal, explainable logic programs from SVM models, addressing local optima issues in traditional ILP.

Findings

Outperforms FOIL in number of induced clauses

Achieves better classification metrics

Effectively captures SVM model's logic

Abstract

We focus on the problem of inducing logic programs that explain models learned by the support vector machine (SVM) algorithm. The top-down sequential covering inductive logic programming (ILP) algorithms (e.g., FOIL) apply hill-climbing search using heuristics from information theory. A major issue with this class of algorithms is getting stuck in a local optimum. In our new approach, however, the data-dependent hill-climbing search is replaced with a model-dependent search where a globally optimal SVM model is trained first, then the algorithm looks into support vectors as the most influential data points in the model, and induces a clause that would cover the support vector and points that are most similar to that support vector. Instead of defining a fixed hypothesis search space, our algorithm makes use of SHAP, an example-specific interpreter in explainable AI, to determine a relevant set of features. This approach yields an algorithm that captures SVM model's underlying logic and outperforms %GG: the FOIL algorithm --> other ILP algorithms other ILP algorithms in terms of the number of induced clauses and classification evaluation metrics. This paper is under consideration for publication in the journal of "Theory and practice of logic programming".