Saved in:
Bibliographic Details
Main Authors: Prado-Romero, Mario Alfonso, Prenkaj, Bardh, Stilo, Giovanni, Giannotti, Fosca
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.12089
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917690263732224
author Prado-Romero, Mario Alfonso
Prenkaj, Bardh
Stilo, Giovanni
Giannotti, Fosca
author_facet Prado-Romero, Mario Alfonso
Prenkaj, Bardh
Stilo, Giovanni
Giannotti, Fosca
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2210_12089
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
Prado-Romero, Mario Alfonso
Prenkaj, Bardh
Stilo, Giovanni
Giannotti, Fosca
Machine Learning
Artificial Intelligence
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.
title A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2210.12089