EUVIMEDEUVIMED entdecken
Crossref

Self-Interpretable Graph Learning with Sufficient and Necessary Explanations

Jiale Deng, Yanyan Shen

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (10) · 11749-11756

DOI: 10.1609/aaai.v38i10.29059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jiale Deng und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Self-interpretable graph learning methods provide insights to unveil the black-box nature of GNNs by providing predictions with built-in explanations. However, current works suffer from performance degradation compared to GNNs trained without built-in explanations. We argue the main reason is that they fail to generate explanations satisfying both sufficiency and necessity, and the biased explanations further hurt GNNs' performance. In this work, we propose a novel framework for generating SUfficient aNd NecessarY explanations (SUNNY-GNN for short) that benefit GNNs' predictions. The key idea is to conduct augmentations by structurally perturbing given explanations and employ a contrastive loss to guide the learning of explanations toward sufficiency and necessity directions. SUNNY-GNN introduces two coefficients to generate hard and reliable contrastive samples. We further extend SUNNY-GNN to heterogeneous graphs. Empirical results on various GNNs and real-world graphs show that SUNNY-GNN yields accurate predictions and faithful explanations, outperforming the state-of-the-art methods by improving 3.5% prediction accuracy and 13.1% explainability fidelity on average. Our code and data are available at https://github.com/SJTU-Quant/SUNNY-GNN.

Zitieren

APA

Deng, J., & Shen, Y. (2024). Self-Interpretable Graph Learning with Sufficient and Necessary Explanations. Proceedings of the AAAI Conference on Artificial Intelligence, 38(10), 11749-11756. https://doi.org/10.1609/aaai.v38i10.29059

Vancouver

Deng J, Shen Y. Self-Interpretable Graph Learning with Sufficient and Necessary Explanations. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(10):11749-11756. doi:10.1609/aaai.v38i10.29059

BibTeX
@article{Deng2024,
  author = {Deng, Jiale and Shen, Yanyan},
  title = {Self-Interpretable Graph Learning with Sufficient and Necessary Explanations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {10},
  pages = {11749--11756},
  doi = {10.1609/aaai.v38i10.29059}
}
Kostenlos starten →