Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.
A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation / Prado-Romero, M. A.; Prenkaj, B.; Stilo, G.; Giannotti, F.. - In: ACM COMPUTING SURVEYS. - ISSN 0360-0300. - 56:7(2024), pp. 1-37. [10.1145/3618105]
A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation
Prenkaj, B.
Secondo
Formal Analysis
;Stilo, G.
Penultimo
Formal Analysis
;Giannotti, F.Ultimo
Writing – Review & Editing
2024
Abstract
Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.File | Dimensione | Formato | |
---|---|---|---|
3618105.pdf
accesso aperto
Note: Prado-Romero_A Survey_2024
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
937.86 kB
Formato
Adobe PDF
|
937.86 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.