Declarative Reasoning on Explanations Using Constraint Logic Programming

TL;DR

REASONX is a novel explanation method for machine learning models that uses Constraint Logic Programming to incorporate background knowledge, enable interactivity, and provide declarative, multi-level explanations for decision trees.

Contribution

It introduces REASONX, a CLP-based framework that enhances explainability in AI by allowing declarative, interactive, and knowledge-informed explanations for decision trees and surrogate models.

Findings

REASONX effectively incorporates background knowledge into explanations.

It supports interactive explanations at multiple abstraction levels.

The architecture combines Python and Prolog for flexible, declarative reasoning.

Abstract

Explaining opaque Machine Learning (ML) models is an increasingly relevant problem. Current explanation in AI (XAI) methods suffer several shortcomings, among others an insufficient incorporation of background knowledge, and a lack of abstraction and interactivity with the user. We propose REASONX, an explanation method based on Constraint Logic Programming (CLP). REASONX can provide declarative, interactive explanations for decision trees, which can be the ML models under analysis or global/local surrogate models of any black-box model. Users can express background or common sense knowledge using linear constraints and MILP optimization over features of factual and contrastive instances, and interact with the answer constraints at different levels of abstraction through constraint projection. We present here the architecture of REASONX, which consists of a Python layer, closer to the user, and a CLP layer. REASONX's core execution engine is a Prolog meta-program with declarative semantics in terms of logic theories.