Explainable AI for Classification using Probabilistic Logic Inference

TL;DR

This paper introduces an explainable classification method that constructs a symbolic knowledge base from data and uses probabilistic inference with linear programming, achieving accuracy comparable to traditional models while providing transparent explanations.

Contribution

The work presents a novel explainable classification approach combining symbolic knowledge bases and probabilistic inference, matching the performance of standard classifiers.

Findings

Achieves classification accuracy comparable to random forests, SVMs, and neural networks.

Provides feature-based explanations similar to SHAP.

Performs well on diverse synthetic and real datasets.

Abstract

The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that produce a high level of prediction accuracy as well as transparent explanations are valuable. In this work, we present an explainable classification method. Our method works by first constructing a symbolic Knowledge Base from the training data, and then performing probabilistic inferences on such Knowledge Base with linear programming. Our approach achieves a level of learning performance comparable to that of traditional classifiers such as random forests, support vector machines and neural networks. It identifies decisive features that are responsible for a classification as explanations and produces results similar to the ones found by SHAP, a state of the art Shapley Value based method. Our algorithms perform well on a range of synthetic and non-synthetic data sets.