Node Classification 벤치마크
Node Classification on Eximtradedata
Accuracy
- 2014-03-26 — DeepWalk: Accuracy 22.5
- 2017-04-11 — Struc2vec: Accuracy 22.8
| Rank | Model | Accuracy | Macro-F1 | Macro F1 | Micro F1 | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|
| 1 | Struc2vec | 22.80% | 0.216 | – | – | struc2vec: Learning Node Representations from Structural Identity | shenweichen/GraphEmbedding · leoribeiro/struc2vec · snap-stanford/graphwave · +2 | 2017 |
| 2 | DeepWalk | 22.5% | 0.214 | – | – | DeepWalk: Online Learning of Social Representations | PaddlePaddle/PaddleRec · shenweichen/GraphEmbedding · williamleif/GraphSAGE · +11 | 2014 |
| 3 | LINE | 20.50% | 0.192 | – | – | LINE: Large-scale Information Network Embedding | shenweichen/GraphEmbedding · tangjianpku/LINE · ink-usc/request · +6 | 2015 |
| 4 | GraRep | – | 0.3093 | – | – | GraRep: Learning Graph Representations with Global Structural Information | benedekrozemberczki/karateclub · benedekrozemberczki/GraRep | 2015 |
| 5 | DAOR | – | – | 17.25 | 33.05 | Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection | eXascaleInfolab/daor | 2019 |