期刊
NEURAL NETWORKS
卷 161, 期 -, 页码 505-514出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2023.01.051
关键词
Graph neural networks; Positional embedding; Structural embedding; Node classification; Graph classification
This paper proposes a new class of GNNs called SP-GNNs, which enhance the expressive power of GNN architectures by incorporating a position encoder and a structure encoder. The experiments show significant improvement in classification using SP-GNNs on various graph datasets.
Graph neural network (GNN) is a powerful model for learning from graph data. However, existing GNNs may have limited expressive power, especially in terms of capturing adequate structural and positional information of input graphs. Structure properties and node position information are unique to graphstructured data, but few GNNs are capable of capturing them. This paper proposes Structure- and Position-aware Graph Neural Networks (SP-GNN), a new class of GNNs offering generic and expressive power of graph data. SP-GNN enhances the expressive power of GNN architectures by incorporating a near-isometric proximity-aware position encoder and a scalable structure encoder. Further, given a GNN learning task, SP-GNN can be used to analyze positional and structural awareness of GNN tasks using the corresponding embeddings computed by the encoders. The awareness scores can guide fusion strategies of the extracted positional and structural information with raw features for better performance of GNNs on downstream tasks. We conduct extensive experiments using SP-GNN on various graph datasets and observe significant improvement in classification over existing GNN models.(c) 2023 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据