Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis

TL;DR

This paper explores declarative, answer-set programming methods for score-based explanations in data management and machine learning, emphasizing counterfactual reasoning to enhance interpretability and flexibility.

Contribution

It introduces a novel declarative approach using answer-set programming for counterfactual analysis in score-based explanations, demonstrating its versatility.

Findings

Effective counterfactual reasoning methods demonstrated

Flexible declarative explanations showcased through examples

Enhanced interpretability in data and machine learning models

Abstract

We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning. The focus is on work done by the author and collaborators. Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation. Several examples that illustrate the flexibility of these methods are shown.