Causal Inference Explanations for Graph Neural Networks

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.

Access paper here

Bibtex:

@inproceedings{Kumar2024causal-inference-explanations,
    author = "Kumar, Sahil Satish and Soares, Claudia",
    title = "Causal Inference Explanations for Graph Neural Networks",
    booktitle = "Causal@UAI2024 Poster",
    url = "https://openreview.net/forum?id=xB99i5yHtm",
    year = "2024",
    eprint = "https://openreview.net/pdf?id=kumar|causal\\_inference\\_explanations\\_for\\_graph\\_neural\\_networks",
    organization = "auai.org/UAI/2024/Workshop/Causal",
    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."
}