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

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 local optima. 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 the SVM model’s underlying logic and outperforms other ILP algorithms in terms of the number of induced clauses and classification evaluation metrics.

Explainability as the key ingredient for AI adoption in Industry 5.0 settings

“…These methods provide justification for the predictions made by ensemble models. Explanation by simplification, feature attribution, and visualizations have been commonly used to shed light on SVM models and understand how they make decisions (Van Belle et al, 2016 ; Shakerin and Gupta, 2020 ). Similarly, deep learning models, including Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), require specialized explainability methods.…”

The Digital Intelligent Application of Experiment Teaching Based on SVM-Adaboost Algorithm

“…The overall sample size was small. Therefore, support vector machine algorithm model is the first choice in this study [9]. Combining support vector machine algorithm with other algorithms can make up the deficiency of support vector machine and improve the actual efficiency of research.…”

Towards Understanding Human Functional Brain Development With Explainable Artificial Intelligence: Challenges and Perspectives

“…Although the above reviewed works involving SVM, i.e. Moezzi et al [46] (section III-A1(a)) and Cauchoix et al [55] (section III-A1(f)) are non-explainable methods, other works involving SVMs in particular have investigated gaining an insight into the inference mechanism by using logic programming [56], and decision trees [57]. Given the aforementioned limitations of non-explainable AI methods reviewed to inform the underlying brain mechanisms, we review the XAI methods in the next section.…”