Geom-GCN-I

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Graphs6 results

Node ClassificationonWisconsin
Accuracy· 2020-02-13
58.24
best: 88.77 (MGNN + Hetero-S (6 layers))
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287
Node ClassificationonSquirrel
Accuracy· 2020-02-13
33.32
best: 57.83 (JKNet + Hetero-S (8 layers))
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287
Node ClassificationonTexas
Accuracy· 2020-02-13
57.58
best: 93.09 (MGNN + Hetero-S (8 layers))
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287
Node ClassificationonCornell
Accuracy· 2020-02-13
56.76
best: 82.4324 (FDGATII)
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287
Node ClassificationonChameleon
Accuracy· 2020-02-13
60.31
best: 70.18 (JKNet + Hetero-S (8 layers))
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287
Node ClassificationonActor
Accuracy· 2020-02-13
29.09
best: 35.99 (MGNN + Hetero-S (4 layers))
Geom-GCN: Geometric Graph Convolutional Networks arXiv:2002.05287