White-box induction from SVM models: explainable AI with logic programming

DOI10.1017/S1471068420000356MaRDI QIDQ5140006zbMATH OpenDBLPWikidataFDO

Authors Farhad Shakerin, Gopal Gupta

Publication date 13 December 2020

Published in Theory and Practice of Logic Programming (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2008.03301

zbMATH Keywords

data miningexplainable AIinductive logic programmingmachine learning

Mathematics Subject Classification ID

Logic programming (68N17) Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

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".

Recommendations

• Taming the complexity of inductive logic programming
• Explaining AI decisions using efficient methods for learning sparse Boolean formulae
• A comparative study of three neural-symbolic approaches to inductive logic programming
• scientific article; zbMATH DE number 1368930
• Inductive Logic Programming: Theory and methods

Cites work

• A new algorithm to automate inductive learning of default theories
• Computational Methods in Systems Biology
• Frequent Pattern Mining
• scientific article; zbMATH DE number 1974050 (Why is no real title available?)
• scientific article; zbMATH DE number 3412190 (Why is no real title available?)
• ILP turns 20. Biography and future challenges
• Induction from answer sets in nonmonotonic logic programs
• Inductive logic programming
• Integrating naïve Bayes and FOIL
• Knowledge Representation, Reasoning and Declarative Problem Solving
• Logic Programming
• Rule Extraction from Support Vector Machines
• Rule extraction from support vector machines: an introduction
• Rule extraction from support vector machines: an overview of issues and application in credit scoring
• Support-vector networks
• WEKA -- experiences with a Java open-source project

Cited in

(2)

• FOLD-RM: A Scalable, Efficient, and Explainable Inductive Learning Algorithm for Multi-Category Classification of Mixed Data
• Generating explainable rule sets from tree-ensemble learning methods by answer set programming

Describes a project that uses

Uses Software

• WEKA
• XGBoost
• kFOIL
• UCI
• shap
• nFOIL
• QuickFOIL
• Aleph
• C4.5
• GitHub

This page was built for publication: White-box induction from SVM models: explainable AI with logic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5140006)