Spaceland Embedding of Sparse Stochastic Graphs
About
We introduce a nonlinear method for directly embedding large, sparse, stochastic graphs into low-dimensional spaces, without requiring vertex features to reside in, or be transformed into, a metric space. Graph data and models are prevalent in real-world applications. Direct graph embedding is fundamental to many graph analysis tasks, in addition to graph visualization. We name the novel approach SG-t-SNE, as it is inspired by and builds upon the core principle of t-SNE, a widely used method for nonlinear dimensionality reduction and data visualization. We also introduce t-SNE-$\Pi$, a high-performance software for 2D, 3D embedding of large sparse graphs on personal computers with superior efficiency. It empowers SG-t-SNE with modern computing techniques for exploiting in tandem both matrix structures and memory architectures. We present elucidating embedding results on one synthetic graph and four real-world networks.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Node Classification | Photo (test) | Mean Accuracy92.8 | 241 | |
| Link Prediction | Citeseer | AUC97.6 | 174 | |
| Link Prediction | Cora | AUC (Cora)95.5 | 94 | |
| Node Classification | Cora (random) | Accuracy64 | 79 | |
| Link Prediction | Photo | AUC-ROC96.1 | 52 | |
| Link Prediction | Computers | AUC-ROC93.8 | 50 | |
| Link Prediction | arXiv | AUC95.3 | 40 | |
| Link Prediction | Pubmed | AUC-ROC96 | 29 | |
| 2-hop neighbor recall | Computer | Top-10 2-hop Recall21.9 | 12 | |
| KNN Classification | MNIST (test) | Accuracy96.9 | 12 |