EUVIMEDDécouvrir EUVIMED
Open access · CC BY 4.0

Explaining the Explainers in Graph Neural Networks: a Comparative Study

Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Lio, Bruno Lepri, Andrea Passerini

ACM Computing Surveys · 2025-05-31 · 57 (5) · 1-37

DOI: 10.1145/3696444 ↗

At a glance

Journal article in ACM Computing Surveys, published online on 2025-01-09. Written by Antonio Longa and 6 co-authors. Cited 52 times so far (Crossref); 130 references. The full text is freely available (open access, CC BY 4.0). Funded by: MUR PNRR project FAIR - Future AI Research, NextGenerationEU, Horizon Europe Programme.

RésuméRéférences bibliographiquesCiteRelated studies

Abstract (original language)

Following a fast initial breakthrough in graph-based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable or which explainer should be preferred in a given setting. In this survey we fill these gaps by devising a systematic experimental study, which tests 12 explainers on eight representative message-passing architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.

Funding

  • MUR PNRR project FAIR - Future AI Research
  • NextGenerationEU
  • Horizon Europe Programme
  • European Union’s Horizon research and innovation

Cite

APA

Longa, A., Azzolin, S., Santin, G., Cencetti, G., Lio, P., Lepri, B., & Passerini, A. (2025). Explaining the Explainers in Graph Neural Networks: a Comparative Study. ACM Computing Surveys, 57(5), 1-37. https://doi.org/10.1145/3696444

Vancouver

Longa A, Azzolin S, Santin G, Cencetti G, Lio P, Lepri B, et al. Explaining the Explainers in Graph Neural Networks: a Comparative Study. ACM Computing Surveys. 2025;57(5):1-37. doi:10.1145/3696444

BibTeX
@article{Longa2025,
  author = {Longa, Antonio and Azzolin, Steve and Santin, Gabriele and Cencetti, Giulia and Lio, Pietro and Lepri, Bruno and Passerini, Andrea},
  title = {Explaining the Explainers in Graph Neural Networks: a Comparative Study},
  journal = {ACM Computing Surveys},
  year = {2025},
  volume = {57},
  number = {5},
  pages = {1--37},
  doi = {10.1145/3696444}
}
Start for free →