A Decoupled Graph Convolutional Network with Dual Adaptive Propagation Mechanism for Homophily and Heterophily

Haoran Zhang, Yan Yang, Yan Yang, YingLi Zhong

2024

Abstract

Despite the rapid development of graph neural networks (GNNs) for graph representation learning, there are still problems, such as the most classical model GCN and its variants, which is based on the assumption of homophily is proposed, making it difficult to perform well in heterophilic graphs. To solve this problem, we propose a decoupled graph convolutional network DAP-GCN with dual adaptive propagation mechanism. It learns node representations from two perspectives: attribute and topology, respectively. In heterophilic graphs, connected nodes are more likely to belong to different classes. To avoid aggregating to irrelevant information, we introduce a class similarity matrix for more accurate aggregation based on the similarity between nodes. In addition, we incorporate the class similarity matrix into the propagation and perform the aggregation in an adaptive manner to further alleviate the over-smoothing issue. Experiments show that DAP-GCN has significant performance improvement in both homophilic and heterophilic datasets, especially in heterophilic datasets.

Paper Citation

in Harvard Style

Zhang H., Yang Y. and Zhong Y. (2024). A Decoupled Graph Convolutional Network with Dual Adaptive Propagation Mechanism for Homophily and Heterophily. In Proceedings of the 1st International Conference on Data Mining, E-Learning, and Information Systems - Volume 1: DMEIS; ISBN 978-989-758-715-3, SciTePress, pages 130-136. DOI: 10.5220/0013010800004536

in Bibtex Style

@conference{dmeis24,
author={Haoran Zhang and Yan Yang and YingLi Zhong},
title={A Decoupled Graph Convolutional Network with Dual Adaptive Propagation Mechanism for Homophily and Heterophily},
booktitle={Proceedings of the 1st International Conference on Data Mining, E-Learning, and Information Systems - Volume 1: DMEIS},
year={2024},
pages={130-136},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013010800004536},
isbn={978-989-758-715-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Mining, E-Learning, and Information Systems - Volume 1: DMEIS
TI - A Decoupled Graph Convolutional Network with Dual Adaptive Propagation Mechanism for Homophily and Heterophily
SN - 978-989-758-715-3
AU - Zhang H.
AU - Yang Y.
AU - Zhong Y.
PY - 2024
SP - 130
EP - 136
DO - 10.5220/0013010800004536
PB - SciTePress