EUVIMEDEUVIMED entdecken
Crossref

Structural Information Enhanced Graph Representation for Link Prediction

Lei Shi, Bin Hu, Deng Zhao, Jianshan He, Zhiqiang Zhang, Jun Zhou

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (13) · 14964-14972

DOI: 10.1609/aaai.v38i13.29417 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Lei Shi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Link prediction is a fundamental task of graph machine learning, and Graph Neural Network (GNN) based methods have become the mainstream approach due to their good performance. However, the typical practice learns node representations through neighborhood aggregation, lacking awareness of the structural relationships between target nodes. Recently, some methods have attempted to address this issue by node labeling tricks. However, they still rely on the node-centric neighborhood message passing of GNNs, which we believe involves two limitations in terms of information perception and transmission for link prediction. First, it cannot perceive long-range structural information due to the restricted receptive fields. Second, there may be information loss of node-centric model on link-centric task. In addition, we empirically find that the neighbor node features could introduce noise for link prediction. To address these issues, we propose a structural information enhanced link prediction framework, which involves removing the neighbor node features while fitting neighborhood graph structures more focused through GNN. Furthermore, we introduce Binary Structural Transformer (BST) to encode the structural relationships between target nodes, complementing the deficiency of GNN. Our approach achieves remarkable results on multiple popular benchmarks, including ranking first on ogbl-ppa, ogbl-citation2 and Pubmed.

Zitieren

APA

Shi, L., Hu, B., Zhao, D., He, J., Zhang, Z., & Zhou, J. (2024). Structural Information Enhanced Graph Representation for Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 14964-14972. https://doi.org/10.1609/aaai.v38i13.29417

Vancouver

Shi L, Hu B, Zhao D, He J, Zhang Z, Zhou J. Structural Information Enhanced Graph Representation for Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(13):14964-14972. doi:10.1609/aaai.v38i13.29417

BibTeX
@article{Shi2024,
  author = {Shi, Lei and Hu, Bin and Zhao, Deng and He, Jianshan and Zhang, Zhiqiang and Zhou, Jun},
  title = {Structural Information Enhanced Graph Representation for Link Prediction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {13},
  pages = {14964--14972},
  doi = {10.1609/aaai.v38i13.29417}
}
Kostenlos starten →