DiConStruct: Causal Concept-based Explanations through Black-Box Distillation

TL;DR

DiConStruct is a novel explanation method that provides causal, concept-based explanations for black-box models, maintaining high fidelity and efficiency without sacrificing predictive performance.

Contribution

It introduces a causal, concept-based explanation approach that distills black-box models into structural causal models, capturing causal relations and ensuring efficiency.

Findings

Higher fidelity in approximating black-box models compared to baselines

Provides causal relations between concepts in explanations

Maintains prediction performance while explaining models

Abstract

Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed using human-interpretable semantic concepts. Moreover, the causal relations between these concepts should be captured by the explainer to allow for reasoning about the explanations. Lastly, explanation methods should be efficient and not compromise the performance of the predictive task. Despite the rapid advances in AI explainability in recent years, as far as we know to date, no method fulfills these three properties. Indeed, mainstream methods for local concept explainability do not produce causal explanations and incur a trade-off between explainability and prediction performance. We present DiConStruct, an explanation method that is both concept-based and causal, with the goal of creating more interpretable local explanations in the form of structural causal models and concept attributions. Our explainer works as a distillation model to any black-box machine learning model by approximating its predictions while producing the respective explanations. Because of this, DiConStruct generates explanations efficiently while not impacting the black-box prediction task. We validate our method on an image dataset and a tabular dataset, showing that DiConStruct approximates the black-box models with higher fidelity than other concept explainability baselines, while providing explanations that include the causal relations between the concepts.