EUVIMEDEUVIMED entdecken
Crossref

Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation

Han Yu, Xiaojuan Zhao, Aiping Li, Kai Chen, Ziniu Liu, Zhichao Peng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (33) · 27917-27924

DOI: 10.1609/aaai.v40i33.40015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Han Yu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple single-relation graphs, and there is still insufficient discussion on the power of GNN to express logical rules in KGs. How to enhance the logical expressive power of GNNs is still a key issue. Motivated by this, we propose Path-Neighbor enhanced GNN (PN-GNN), a method to enhance the logical expressive power of GNN by aggregating node-neighbor embeddings on the reasoning path. First, we analyze the logical expressive power of existing GNN-based methods and point out the shortcomings of the expressive power of these methods. Then, we theoretically investigate the logical expressive power of PN-GNN, showing that it not only has strictly stronger expressive power than C-GNN but also that its (k+1)-hop logical expressiveness is strictly superior to that of k-hop. Finally, we evaluate the logical expressive power of PN-GNN on six synthetic datasets and two real-world datasets. Both theoretical analysis and extensive experiments confirm that PN-GNN enhances the expressive power of logical rules without compromising generalization, as evidenced by its competitive performance in KG reasoning tasks.

Zitieren

APA

Yu, H., Zhao, X., Li, A., Chen, K., Liu, Z., & Peng, Z. (2026). Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(33), 27917-27924. https://doi.org/10.1609/aaai.v40i33.40015

Vancouver

Yu H, Zhao X, Li A, Chen K, Liu Z, Peng Z. Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(33):27917-27924. doi:10.1609/aaai.v40i33.40015

BibTeX
@article{Yu2026,
  author = {Yu, Han and Zhao, Xiaojuan and Li, Aiping and Chen, Kai and Liu, Ziniu and Peng, Zhichao},
  title = {Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {33},
  pages = {27917--27924},
  doi = {10.1609/aaai.v40i33.40015}
}
Kostenlos starten →