Causal Inference Explanations for Graph Neural Networks

Sahil Satish Kumar, Claudia Soares

Keywords: Explainability, Causal Inference, Graph Neural Networks

TL;DR: A causal inference based explanation method for the link predictions returned by Graph Neural Networks.

Abstract: Explainable Artificial Intelligence has emerged, aiming to enhance the trustworthiness of black box models by devising explanation methods that clarify their inner workings. However, prevalent explanation techniques predominantly leverage correlation and association rather than employing causality, a significant aspect of human comprehension. We propose a novel explanation method grounded in causal inference tailored specifically for Graph Neural Networks. Our approach seeks to illuminate the decision-making process of Graph Neural Networks, thereby augmenting their transparency and trustworthiness. We apply our method to the medical referral problem in healthcare.

Submission Number: 26