Gaussian Embedding of Large-scale Attributed Graphs

2 Dec 2019  ·  Bhagya Hettige, Yuan-Fang Li, Weiqing Wang, Wray Buntine ·

Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner. GLACE effectively models uncertainty through Gaussian embeddings, and supports inductive inference of new nodes based on their attributes. In our comprehensive experiments, we evaluate GLACE on real-world graphs, and the results demonstrate that GLACE significantly outperforms state-of-the-art embedding methods on multiple graph analysis tasks.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction ACM GLACE AP 98.24 # 1
AUC 98.34 # 1
Link Prediction Citeseer (nonstandard variant) GLACE AUC 98.43 # 1
AP 98.37 # 1
Link Prediction Cora (nonstandard variant) GLACE AUC 98.6 # 1
AP 98.52 # 1
Link Prediction DBLP GLACE AUC 98.55 # 1
AP 98.4 # 1
Link Prediction Pubmed (nonstandard variant) GLACE AUC 97.82 # 1
AP 97.49 # 1


No methods listed for this paper. Add relevant methods here