Node Classification On Cornell 60 20 20

1:1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	1:1 Accuracy	Paper Title
HH-GAT	72.7 ± 4.26	Half-Hop: A graph upsampling approach for slowing down message passing
ACM-SGC-2	93.77 ± 2.17	Revisiting Heterophily For Graph Neural Networks
GAT	76.00 ± 1.01	Graph Attention Networks
GraphSAGE	71.41 ± 1.24	Inductive Representation Learning on Large Graphs
Snowball-3	82.95 ± 2.1	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
ACM-GCN	94.75 ± 3.8	Revisiting Heterophily For Graph Neural Networks
GCN	82.46 ± 3.11	Semi-Supervised Classification with Graph Convolutional Networks
HH-GraphSAGE	74.6 ± 6.06	Half-Hop: A graph upsampling approach for slowing down message passing
GCNII*	90.49 ± 4.45	Simple and Deep Graph Convolutional Networks
ACM-GCN++	93.93 ± 1.05	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	95.9 ± 1.83	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	94.92 ± 2.79	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-2	95.08 ± 3.11	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*	93.44 ± 2.74	Revisiting Heterophily For Graph Neural Networks
MLP-2	91.30 ± 0.70	Revisiting Heterophily For Graph Neural Networks
SGC-1	70.98 ± 8.39	Simplifying Graph Convolutional Networks
FAGCN	88.03 ± 5.6	Beyond Low-frequency Information in Graph Convolutional Networks
SGC-2	72.62 ± 9.92	Simplifying Graph Convolutional Networks
H2GCN	86.23 ± 4.71	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Geom-GCN*	60.81	Geom-GCN: Geometric Graph Convolutional Networks

0 of 36 row(s) selected.