Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning

Junhyun Lee, Bumsoo Kim, Minji Jeon, Jaewoo Kang

Research output: Contribution to journalArticlepeer-review


Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. However, previous works mainly focused on understanding single graph inputs while many real-world applications require pair-wise analysis for graph-structured data (e.g., scene graph matching, code searching, and drug-drug interaction prediction). To this end, recent works have shifted their focus to learning the interaction between pairs of graphs. Despite their improved performance, these works were still limited in that the interactions were considered at the node-level, resulting in high computational costs and suboptimal performance. To address this issue, we propose a novel and efficient graph-level approach for extracting interaction representations using co-attention in graph pooling. Our method, Co-Attention Graph Pooling (CAGPool), exhibits competitive performance relative to existing methods in both classification and regression tasks using real-world datasets, while maintaining lower computational complexity.

Original languageEnglish
Pages (from-to)78549-78560
Number of pages12
JournalIEEE Access
Publication statusPublished - 2023

Bibliographical note

Publisher Copyright:
© 2013 IEEE.


  • Graph neural networks
  • drug-drug interaction
  • graph edit distance
  • graph pooling
  • pairwise graph interaction

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering


Dive into the research topics of 'Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning'. Together they form a unique fingerprint.

Cite this