SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning
Article
Wang, Jialin, Qu, Xiaoru, Bai, Jinze, Li, Zhao, Zhang, Ji and Gao, Jun. 2023. "SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning." IEEE Transactions on Knowledge and Data Engineering. 35 (5), pp. 5216-5229. https://doi.org/10.1109/TKDE.2022.3148272
| Article Title | SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning |
|---|---|
| ERA Journal ID | 17876 |
| Article Category | Article |
| Authors | Wang, Jialin, Qu, Xiaoru, Bai, Jinze, Li, Zhao, Zhang, Ji and Gao, Jun |
| Journal Title | IEEE Transactions on Knowledge and Data Engineering |
| Journal Citation | 35 (5), pp. 5216-5229 |
| Number of Pages | 14 |
| Year | 2023 |
| Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
| Place of Publication | United States |
| ISSN | 1041-4347 |
| 1558-2191 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1109/TKDE.2022.3148272 |
| Web Address (URL) | https://ieeexplore.ieee.org/abstract/document/9705119 |
| Abstract | Unsupervised graph embedding method generates node embeddings to preserve structural and content features in a graph without human labeling burden. However, most unsupervised graph representation learning methods suffer issues like poor scalability or limited utilization of content/structural relationships, especially on attributed graphs. In this paper, we propose SAGES, a graph sampling based autoencoder framework, which can promote both the performance and scalability of unsupervised learning on attributed graphs. Specifically, we propose a graph sampler that considers both the node connections and node attributes, thus nodes having a high influence on each other will be sampled in the same subgraph. After that, an unbiased Graph Autoencoder (GAE) with structure-level, content-level, and community-level reconstruction loss is built on the properly-sampled subgraphs in each epoch. The time and space complexity analysis is carried out to show the scalability of SAGES. We conducted experiments on three medium-size attributed graphs and three large attributed graphs. Experimental results illustrate that SAGES achieves the competitive performance in unsupervised attributed graph learning on a variety of node classification benchmarks and node clustering benchmarks. |
| Keywords | graph neural network; Machine learning; unsupervised graph learning |
| ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | Peking University, China |
| Zhejiang University, China | |
| Zhejiang Lab, China | |
| University of Southern Queensland |
Permalink -
https://research.usq.edu.au/item/z2713/sages-scalable-attributed-graph-embedding-with-sampling-for-unsupervised-learning
41
total views0
total downloads2
views this month0
downloads this month