Toward Faithful Class-Level Self-Explainability in Graph Neural Networks by Subgraph Dependencies
IEEE Transactions on Knowledge and Data Engineering · 2026-12 · 38 (12) · 8542-8555
DOI: 10.1109/tkde.2026.3730527 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-12. Verfasst von Fanzhen Liu und 8 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Gefördert von: ARC Projects, Macquarie University Graph Data Science Research Network.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- ARC Projects
- Macquarie University Graph Data Science Research Network
Zitieren
APA
Liu, F., Ma, X., Yang, J., Abuadbba, A., Moore, K., Nepal, S., Paris, C., Sheng, Q. Z., & Wu, J. (2026). Toward Faithful Class-Level Self-Explainability in Graph Neural Networks by Subgraph Dependencies. IEEE Transactions on Knowledge and Data Engineering, 38(12), 8542-8555. https://doi.org/10.1109/tkde.2026.3730527
Vancouver
Liu F, Ma X, Yang J, Abuadbba A, Moore K, Nepal S, et al. Toward Faithful Class-Level Self-Explainability in Graph Neural Networks by Subgraph Dependencies. IEEE Transactions on Knowledge and Data Engineering. 2026;38(12):8542-8555. doi:10.1109/tkde.2026.3730527
BibTeX
@article{Liu2026,
author = {Liu, Fanzhen and Ma, Xiaoxiao and Yang, Jian and Abuadbba, Alsharif and Moore, Kristen and Nepal, Surya and Paris, Cecile and Sheng, Quan Z. and Wu, Jia},
title = {Toward Faithful Class-Level Self-Explainability in Graph Neural Networks by Subgraph Dependencies},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {12},
pages = {8542--8555},
doi = {10.1109/tkde.2026.3730527}
}
EUVIMED