Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning

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 match...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Lee, Junhyun, Kim, Bumsoo, Jeon, Minji, Kang, Jaewoo
Format: Article
Language:English
Subjects:
Computing costs
Graph matching
Graph neural networks
Graphical representations
Learning
Structured data
Task complexity
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2307.15377