SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning

Jialin Wang, Xiaoru Qu, Jinze Bai, Zhao Li, Ji Zhang, Jun Gao

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.
BibTeX
@article{wang2023sages,
  author = {Jialin Wang and Xiaoru Qu and Jinze Bai and Zhao Li and Ji Zhang and Jun Gao},
  title = {{SAGES: Scalable Attributed Graph Embedding With Sampling for Unsupervised Learning}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2023},
  url = {https://openreview.net/forum?id=OOIt18PloU},
}

Loading related content...

Figure