English

Evaluating Link Prediction Explanations for Graph Neural Networks

Machine Learning 2023-08-04 v1 Artificial Intelligence

Abstract

Graph Machine Learning (GML) has numerous applications, such as node/graph classification and link prediction, in real-world domains. Providing human-understandable explanations for GML models is a challenging yet fundamental task to foster their adoption, but validating explanations for link prediction models has received little attention. In this paper, we provide quantitative metrics to assess the quality of link prediction explanations, with or without ground-truth. State-of-the-art explainability methods for Graph Neural Networks are evaluated using these metrics. We discuss how underlying assumptions and technical details specific to the link prediction task, such as the choice of distance between node embeddings, can influence the quality of the explanations.

Keywords

Cite

@article{arxiv.2308.01682,
  title  = {Evaluating Link Prediction Explanations for Graph Neural Networks},
  author = {Claudio Borile and Alan Perotti and André Panisson},
  journal= {arXiv preprint arXiv:2308.01682},
  year   = {2023}
}

Comments

This work has been accepted to be presented to The 1st World Conference on eXplainable Artificial Intelligence (xAI 2023), July 26-28, 2023 - Lisboa, Portugal

R2 v1 2026-06-28T11:47:14.303Z