CoGS: Causality Constrained Counterfactual Explanations using goal-directed ASP

TL;DR

This paper introduces CoGS, a framework that generates causally consistent counterfactual explanations for rule-based machine learning models using goal-directed ASP, enhancing transparency and interpretability.

Contribution

CoGS is the first framework to incorporate causal dependencies in counterfactual explanations using goal-directed ASP for rule-based models.

Findings

CoGS produces realistic, causally consistent counterfactuals.

It effectively finds paths from undesired to desired outcomes.

The framework improves interpretability of rule-based models.

Abstract

Machine learning models are increasingly used in areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, and individuals need explanations to understand decisions, especially for the ones not desired by the user. Ethical and legal considerations require informing individuals of changes in input attribute values (features) that could lead to a desired outcome for the user. Our work aims to generate counterfactual explanations by considering causal dependencies between features. We present the CoGS (Counterfactual Generation with s(CASP)) framework that utilizes the goal-directed Answer Set Programming system s(CASP) to generate counterfactuals from rule-based machine learning models, specifically the FOLD-SE algorithm. CoGS computes realistic and causally consistent changes to attribute values taking causal dependencies between them into account. It finds a path from an undesired outcome to a desired one using counterfactuals. We present details of the CoGS framework along with its evaluation.