Actionable and diverse counterfactual explanations incorporating domain knowledge and causal constraints

TL;DR

This paper introduces DANCE, a method for generating diverse, plausible, and actionable counterfactual explanations that incorporate domain knowledge and causal constraints, improving interpretability in real-world applications.

Contribution

It proposes a novel approach that integrates feature dependencies and causal constraints into counterfactual generation, ensuring realistic and domain-relevant explanations.

Findings

Outperforms existing methods on 140 datasets

Produces more plausible and actionable counterfactuals

Balances diversity, plausibility, and sparsity effectively

Abstract

Counterfactual explanations enhance the actionable interpretability of machine learning models by identifying the minimal changes required to achieve a desired outcome of the model. However, existing methods often ignore the complex dependencies in real-world datasets, leading to unrealistic or impractical modifications. Motivated by cybersecurity applications in the email marketing domain, we propose a method for generating Diverse, Actionable, and kNowledge-Constrained Explanations (DANCE), which incorporates feature dependencies and causal constraints to ensure plausibility and real-world feasibility of counterfactuals. Our method learns linear and nonlinear constraints from data or integrates expert-provided dependency graphs, ensuring counterfactuals are plausible and actionable. By maintaining consistency with feature relationships, the method produces explanations that align with real-world constraints. Additionally, it balances plausibility, diversity, and sparsity, effectively addressing key limitations in existing algorithms. The work is developed based on a real-life case study with Freshmail, the largest email marketing company in Poland and supported by a joint R&D project Sendguard. Furthermore, we provide an extensive evaluation using 140 public datasets, which highlights its ability to generate meaningful, domain-relevant counterfactuals that outperform other existing approaches based on widely used metrics. The source code for reproduction of the results can be found in a GitHub repository we provide.