k-simplex2vec: a simplicial extension of node2vec
About
We present a novel method of associating Euclidean features to simplicial complexes, providing a way to use them as input to statistical and machine learning tools. This method extends the node2vec algorithm to simplices of higher dimensions, providing insight into the structure of a simplicial complex, or into the higher-order interactions in a graph.
Celia Hacker• 2020
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Node Classification | Citeseer | Accuracy44.22 | 1037 | |
| Node Classification | Cora (test) | Mean Accuracy68.3 | 951 | |
| Node Classification | Pubmed | Accuracy67.21 | 865 | |
| Node Classification | Chameleon (test) | Mean Accuracy49 | 335 | |
| Node Classification | Texas (test) | Mean Accuracy85.12 | 312 | |
| Node Classification | Squirrel (test) | Mean Accuracy39.15 | 301 | |
| Node Classification | Wisconsin (test) | Mean Accuracy87.44 | 279 | |
| Node Classification | Photo (test) | Mean Accuracy89.08 | 125 | |
| Node Classification | Computers (test) | Mean Accuracy84.15 | 109 |
Showing 9 of 9 rows