Generating Causally Compliant Counterfactual Explanations using ASP

TL;DR

This work tackles the realism gap in counterfactual explanations by enforcing causal dependencies among features. It introduces CoGS, a Counterfactual Generation with $s(CASP)$ framework that encodes feature knowledge, decision rules, and causal constraints in an ASP program and solves a planning problem from a negative state $i$ to a causally feasible positive state $g$. The approach relies on a rule-based learner (e.g., $FOLD{-}SE$) to discover causal rules and uses the goal-directed $s(CASP)$ ASP system to generate minimal, actionable intervention paths. Preliminary experiments on the German, Adult, and Car Evaluation datasets show multiple counterfactual sets and feasible computation times, demonstrating practicality for rule-based models and potential extension to statistical models via approximations. Overall, the framework advances explainable recourse by delivering realistic, causally coherent counterfactual explanations that can guide user actions.

Abstract

This research is focused on generating achievable counterfactual explanations. Given a negative outcome computed by a machine learning model or a decision system, the novel CoGS approach generates (i) a counterfactual solution that represents a positive outcome and (ii) a path that will take us from the negative outcome to the positive one, where each node in the path represents a change in an attribute (feature) value. CoGS computes paths that respect the causal constraints among features. Thus, the counterfactuals computed by CoGS are realistic. CoGS utilizes rule-based machine learning algorithms to model causal dependencies between features. The paper discusses the current status of the research and the preliminary results obtained.

Figures (1)

• Figure 1: Top: Example 1 shows how John goes from being rejected for a loan to having his loan approved. Here the bank only considers the bank balance for loan approval. John does a direct action to increase his bank balance to $\$60000$. Bottom: Example 2 shows how John goes from being rejected for a loan to having his loan approved. Here the bank considers both bank balance as well as credit score for loan approval. While the bank balance is directly altered by John, altering the credit score requires John to directly alter his debt obligations first. After clearing his debt, the causal effect of having $\$0$debt increases John's credit score to $620\ point$. This is the causal action