Node Classification
Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.
Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.
( Image credit: Fast Graph Representation Learning With PyTorch Geometric )
Papers
Showing 276–300 of 1860 papers
All datasetsCiteseerPubmedCoraCiteSeer with Public Split: fixed 20 nodes per classPubMed with Public Split: fixed 20 nodes per classCora with Public Split: fixed 20 nodes per classPPICoauthor CSCora (0.5%)Cora (1%)Cora (3%)PubMed (0.03%)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | NodeNet | Accuracy | 80.09 | — | Unverified |
| 2 | SplineCNN | Accuracy | 79.2 | — | Unverified |
| 3 | PathNet | Accuracy (%) | 77.98 | — | Unverified |
| 4 | 3ference | Accuracy | 76.33 | — | Unverified |
| 5 | MMA | Accuracy | 76.3 | — | Unverified |
| 6 | PPNP | Accuracy | 75.83 | — | Unverified |
| 7 | CoLinkDist | Accuracy | 75.79 | — | Unverified |
| 8 | CoLinkDistMLP | Accuracy | 75.77 | — | Unverified |
| 9 | APPNP | Accuracy | 75.73 | — | Unverified |
| 10 | Cleora | Accuracy | 75.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | NodeNet | Accuracy | 90.21 | — | Unverified |
| 2 | CoLinkDist | Accuracy | 89.58 | — | Unverified |
| 3 | CoLinkDistMLP | Accuracy | 89.53 | — | Unverified |
| 4 | PathNet | Accuracy (%) | 88.92 | — | Unverified |
| 5 | 3ference | Accuracy | 88.9 | — | Unverified |
| 6 | SplineCNN | Accuracy | 88.88 | — | Unverified |
| 7 | LinkDist | Accuracy | 88.86 | — | Unverified |
| 8 | LinkDistMLP | Accuracy | 88.79 | — | Unverified |
| 9 | PairE | F1 | 88.57 | — | Unverified |
| 10 | GCN + Mixup | Accuracy | 87.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LinkDist | Accuracy | 88.24 | — | Unverified |
| 2 | CoLinkDist | Accuracy | 87.89 | — | Unverified |
| 3 | 3ference | Accuracy | 87.78 | — | Unverified |
| 4 | LinkDistMLP | Accuracy | 87.58 | — | Unverified |
| 5 | CoLinkDistMLP | Accuracy | 87.54 | — | Unverified |
| 6 | Cleora | Accuracy | 86.8 | — | Unverified |
| 7 | NodeNet | Accuracy | 86.8 | — | Unverified |
| 8 | MMA | Accuracy | 85.8 | — | Unverified |
| 9 | GResNet(GAT) | Accuracy | 85.5 | — | Unverified |
| 10 | TransGNN | 1:1 Accuracy | 85.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | OGC | Accuracy | 77.5 | — | Unverified |
| 2 | LDS-GNN | Accuracy | 75 | — | Unverified |
| 3 | CPF-tra-APPNP | Accuracy | 74.6 | — | Unverified |
| 4 | G3NN | Accuracy | 74.5 | — | Unverified |
| 5 | GEM | Accuracy | 74.2 | — | Unverified |
| 6 | GGCM | Accuracy | 74.2 | — | Unverified |
| 7 | Truncated Krylov | Accuracy | 73.86 | — | Unverified |
| 8 | SSGC | Accuracy | 73.6 | — | Unverified |
| 9 | OKDEEM | Accuracy | 73.53 | — | Unverified |
| 10 | GCNII | Accuracy | 73.4 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | OGC | Accuracy | 83.4 | — | Unverified |
| 2 | CPF-tra-GCNII | Accuracy | 83.2 | — | Unverified |
| 3 | DSGCN | Accuracy | 81.9 | — | Unverified |
| 4 | Truncated Krylov | Accuracy | 81.7 | — | Unverified |
| 5 | SuperGAT MX | Accuracy | 81.7 | — | Unverified |
| 6 | G-APPNP | Accuracy | 80.95 | — | Unverified |
| 7 | GGCM | Accuracy | 80.8 | — | Unverified |
| 8 | GCN(predicted-targets) | Accuracy | 80.42 | — | Unverified |
| 9 | SSGC | Accuracy | 80.4 | — | Unverified |
| 10 | GCNII | Accuracy | 80.2 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | OGC | Accuracy | 86.9 | — | Unverified |
| 2 | GCN-TV | Accuracy | 86.3 | — | Unverified |
| 3 | GCNII | Accuracy | 85.5 | — | Unverified |
| 4 | CPF-ind-APPNP | Accuracy | 85.3 | — | Unverified |
| 5 | AIR-GCN | Accuracy | 84.7 | — | Unverified |
| 6 | H-GCN | Accuracy | 84.5 | — | Unverified |
| 7 | G-APPNP | Accuracy | 84.31 | — | Unverified |
| 8 | SuperGAT MX | Accuracy | 84.3 | — | Unverified |
| 9 | DSGCN | Accuracy | 84.2 | — | Unverified |
| 10 | LDS-GNN | Accuracy | 84.1 | — | Unverified |