Table 4 The table reports the Matthews correlation coefficient (MCC) for 11 node-level classification tasks, presented as mean ± standard deviation over 5 different runs
From: An end-to-end attention-based approach for learning on graphs
Dataset (↑) | GCN | GAT | GATv2 | PNA | Graphormer | TokenGT | GPS | NSA | |
|---|---|---|---|---|---|---|---|---|---|
PPI | 0.98 ± 0.00 | 0.99 ± 0.00 | 0.98 ± 0.01 | 0.99 ± 0.00 | N/A | N/A | N/A | 0.99 ± 0.00 | |
Citation | CiteSeer | 0.61 ± 0.01 | 0.59 ± 0.03 | 0.61 ± 0.01 | 0.51 ± 0.03 | OOM | 0.38 ± 0.02 | 0.54 ± 0.01 | 0.63 ± 0.00 |
Cora | 0.77 ± 0.01 | 0.75 ± 0.01 | 0.73 ± 0.01 | 0.64 ± 0.03 | OOM | 0.37 ± 0.18 | 0.64 ± 0.04 | 0.77 ± 0.00 | |
Heterophily | ROMAN EMPIRE | 0.47 ± 0.00 | 0.74 ± 0.01 | 0.76 ± 0.00 | 0.86 ± 0.00 | N/A | N/A | 0.84 ± 0.01 | 0.87 ± 0.00 |
AMAZON RATINGS | 0.18 ± 0.00 | 0.26 ± 0.01 | 0.25 ± 0.01 | 0.21 ± 0.02 | N/A | N/A | 0.11 ± 0.14 | 0.34 ± 0.01 | |
MINESWEEPER | 0.30 ± 0.00 | 0.48 ± 0.02 | 0.51 ± 0.01 | 0.62 ± 0.04 | N/A | N/A | 0.56 ± 0.01 | 0.69 ± 0.00 | |
TOLOKERS | 0.30 ± 0.01 | 0.38 ± 0.01 | 0.39 ± 0.00 | 0.35 ± 0.05 | N/A | N/A | 0.35 ± 0.02 | 0.43 ± 0.00 | |
SQUIRREL | 0.20 ± 0.01 | 0.24 ± 0.02 | 0.24 ± 0.01 | 0.22 ± 0.01 | 0.10 ± 0.09 | 0.18 ± 0.02 | 0.23 ± 0.02 | 0.29 ± 0.01 | |
CHAMELEON | 0.32 ± 0.01 | 0.24 ± 0.06 | 0.28 ± 0.03 | 0.27 ± 0.03 | 0.25 ± 0.04 | 0.26 ± 0.04 | 0.30 ± 0.08 | 0.39 ± 0.02 | |
Shortest path | ER (15K) | 0.22 ± 0.02 | 0.32 ± 0.00 | 0.32 ± 0.00 | 0.54 ± 0.09 | OOM | 0.06 ± 0.00 | 0.18 ± 0.04 | 0.92 ± 0.01 |
ER (30K) | 0.09 ± 0.03 | 0.10 ± 0.06 | 0.10 ± 0.06 | 0.42 ± 0.05 | OOM | OOM | OOM | 0.87 ± 0.01 |
