Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations
ACM Transactions on Recommender Systems · 30.06.2026 · 4 (2) · 1-26
DOI: 10.1145/3731683 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 22.11.2025. Verfasst von Ziheng Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: National Recovery and Resilience Plan funded by the European Union NextGenerationEU, Italian Ministry of University and Research under the PRIN 2022 program, Sapienza University of Rome - “Progetti di Ricerca Grandi”.
Abstract (Originalsprache)
Recently, graph neural networks (GNNs) have become the new state-of-the-art approach to developing powerful recommender systems. However, it is hard for GNN-based recommender systems to attach tangible explanations of why a specific item ends up in the list of top- k suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate since they are designed to explain node, edge, or graph classification rather than ranking. In this work, we propose GREASE, a novel method for explaining the list of top- k suggested items to a given user provided by any black-box GNN-based recommender system. Specifically, for each recommended item, GREASE first trains a surrogate GNN model on the subgraph obtained as the union of the target user-item pair and its l -hop neighborhood. Then, it jointly generates factual and counterfactual explanations by finding optimal adjacency matrix perturbations to capture the sufficient and necessary conditions for the item to be recommended. Experiments on real-world datasets show that GREASE can generate concise and compelling explanations for popular GNN-based recommender models.
Förderung
- National Recovery and Resilience Plan funded by the European Union NextGenerationEU
- Italian Ministry of University and Research under the PRIN 2022 program
- Sapienza University of Rome - “Progetti di Ricerca Grandi”
Zitieren
APA
Chen, Z., Huang, J., Silvestri, F., Zhang, Y., Ahn, H., & Tolomei, G. (2026). Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations. ACM Transactions on Recommender Systems, 4(2), 1-26. https://doi.org/10.1145/3731683
Vancouver
Chen Z, Huang J, Silvestri F, Zhang Y, Ahn H, Tolomei G. Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations. ACM Transactions on Recommender Systems. 2026;4(2):1-26. doi:10.1145/3731683
BibTeX
@article{Chen2026,
author = {Chen, Ziheng and Huang, Jin and Silvestri, Fabrizio and Zhang, Yongfeng and Ahn, Hongshik and Tolomei, Gabriele},
title = {Joint Factual and Counterfactual Explanations for Top-k GNN-based Recommendations},
journal = {ACM Transactions on Recommender Systems},
year = {2026},
volume = {4},
number = {2},
pages = {1--26},
doi = {10.1145/3731683}
}
EUVIMED