SARW: Similarity-Aware Random Walk for GCN

Author:

Hou Linlin12,Zhang Haixiang2,Hou Qing-Hu2,Guo Alan J.X.2,Wu Ou2,Yu Ting1,Zhang Ji3

Affiliation:

1. Zhejiang Laboratory, Hangzhou, Zhejiang, China

2. Center for Applied Mathematics, Tianjin University, Tianjin, China

3. University of Southern Queensland, Australia

Abstract

Graph Convolutional Network (GCN) is an important method for learning graph representations of nodes. For large-scale graphs, the GCN could meet with the neighborhood expansion phenomenon, which makes the model complexity high and the training time long. An efficient solution is to adopt graph sampling techniques, such as node sampling and random walk sampling. However, the existing sampling methods still suffer from aggregating too many neighbor nodes and ignoring node feature information. Therefore, in this paper, we propose a new subgraph sampling method, namely, Similarity-Aware Random Walk (SARW), for GCN with large-scale graphs. A novel similarity index between two adjacent nodes is proposed, describing the relationship of nodes with their neighbors. Then, we design a sampling probability expression between adjacent nodes using node feature information, degree information, neighbor set information, etc. Moreover, we prove the unbiasedness of the SARW-based GCN model for node representations. The simplified version of SARW (SSARW) has a much smaller variance, which indicates the effectiveness of our subgraph sampling method in large-scale graphs for GCN learning. Experiments on six datasets show our method achieves superior performance over the state-of-the-art graph sampling approaches for the large-scale graph node classification task.

Publisher

IOS Press

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Theoretical Computer Science

Reference40 articles.

1. Y. Zhou, H. Zheng, X. Huang, S. Hao, D. Li and J. Zhao, Graph neural networks: Taxonomy, advances, and trends, ACM Trans. Intell. Syst. Technol. 13(1) (2022).

2. D. Kim and R.o.K. Alice Oh KAIST, How to Find Your Friendly Neighborhood: Graph Attention Design with Self-supervision, in: ICLR, 2021.

3. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks;Liang;Knowledge-Based Systems,2022

4. Z. Wang, Z. Wei, Y. Li, W. Kuang and B. Ding, Graph Neural Networks with Node-Wise Architecture, in: KDD, Association for Computing Machinery, 2022, pp. 1949–1958.

5. F. Wu, A. Souza, T. Zhang, C. Fifty, T. Yu and K. Weinberger, Simplifying Graph Convolutional Networks, in: ICML, 2019, pp. 6861–6871.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3