SARW: Similarity-Aware Random Walk for GCN
Article
Hou, Linlin, Zhang, Haixiang, Hou, Qing-Hu, Guo, Alan J.X., Wu, Ou, Yua, Ting and Zhang, Ji. 2023. "SARW: Similarity-Aware Random Walk for GCN." Intelligent Data Analysis. 27 (6), pp. 1615 -1636. https://doi.org/10.3233/IDA-227085
| Article Title | SARW: Similarity-Aware Random Walk for GCN |
|---|---|
| ERA Journal ID | 17922 |
| Article Category | Article |
| Authors | Hou, Linlin, Zhang, Haixiang, Hou, Qing-Hu, Guo, Alan J.X., Wu, Ou, Yua, Ting and Zhang, Ji |
| Journal Title | Intelligent Data Analysis |
| Journal Citation | 27 (6), pp. 1615 -1636 |
| Number of Pages | 23 |
| Year | 2023 |
| ISSN | 1088-467X |
| 1571-4128 | |
| Digital Object Identifier (DOI) | https://doi.org/10.3233/IDA-227085 |
| Web Address (URL) | https://journals.sagepub.com/doi/abs/10.3233/IDA-227085 |
| 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. |
| Keywords | Graph Convolutional Network; Similarity-Aware Random Walk; subgraph sampling; large-scale graphs; random walk |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460599. Data management and data science not elsewhere classified |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | Zhejiang Lab, China |
| Tianjin University, China | |
| University of Southern Queensland |
Permalink -
https://research.usq.edu.au/item/zq31x/sarw-similarity-aware-random-walk-for-gcn
6
total views0
total downloads6
views this month0
downloads this month