Node Classification On Citeseer Full
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| ASGCN | 79.66% | Adaptive Sampling Towards Fast Graph Representation Learning | |
| GraphSAGE | 71.40% | Inductive Representation Learning on Large Graphs | |
| GCNII* | 77.13% | Simple and Deep Graph Convolutional Networks | |
| IncepGCN+DropEdge | 80.50% | DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | |
| Graph ESN | 74.5±2.1 | Beyond Homophily with Graph Echo State Networks | - |
| FDGATII | 75.6434% | FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping | |
| FastGCN | 77.60% | FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling |
0 of 7 row(s) selected.