Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
Open Access
- 27 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 78549-78560
Abstract
Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. However, many real-world tasks require the analysis of pairs of graph-structured data, such as scene graph matching, code search, and drug-drug interaction prediction. Previous approaches for considering the interaction between these pairs of graphs have focused on the node level, leading to high computational costs and suboptimal performance. To address this issue, we propose a novel, efficient graph-level approach for extracting interaction representation using co-attention in graph pooling. Our method, Co-Attention Graph Pooling (CAGPool), shows competitive performance compared to existing methods on both classification and regression tasks on real-world datasets, while maintaining low computational complexity.Keywords
All Related Versions
Funding Information
- National Research Foundation of Korea (NRF-2023R1A2C3004176)
- Ministry of Science and ICT of Korea Supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP-2023-2020-0-01819)
- Korea Health Industry Development Institute (HR20C0021(3))
- National Research Foundation of Korea (NRF-2022R1F1A1070111)
- Ministry of Science and ICT of Korea Supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP-2022-RS-2022-00156439)
This publication has 23 references indexed in Scilit:
- Similarity Search in Graph Databases: A Multi-Layered Indexing Approach2017
- Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactionsNature Biotechnology, 2017
- Post-marketing withdrawal of 462 medicinal products because of adverse drug reactions: a systematic review of the world literatureBMC Medicine, 2016
- Deep Graph Kernels2015
- A partition-based approach to structure similarity searchProceedings of the VLDB Endowment, 2013
- Graph similarity search with edit distance constraint in large graph databases2013
- Speeding Up Graph Edit Distance Computation through Fast Bipartite Matching2011
- Fast Suboptimal Algorithms for the Computation of Graph Edit Distance2006
- A graph distance metric based on the maximal common subgraphPattern Recognition Letters, 1998
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955