Node Classification 벤치마크
Node Classification on NELL
Accuracy
- 2016-03-29 — Planetoid*: Accuracy 61.9
- 2016-09-09 — GCN: Accuracy 66.0
- 2019-10-24 — DFNet-ATT: Accuracy 68.8
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | DFNet-ATT | 68.8 ± 0.3 | DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters | wokas36/DFNets | 2019 |
| 2 | GCN | 66.0 | Semi-Supervised Classification with Graph Convolutional Networks | dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 | 2016 |
| 3 | GraphVAT | 64.7% | Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure | fulifeng/GraphAT | 2019 |
| 4 | Planetoid* | 61.9% | Revisiting Semi-Supervised Learning with Graph Embeddings | tkipf/gcn · kimiyoung/planetoid · DeepGraphLearning/GMNN · +23 | 2016 |