Node Classification On Texas 60 20 20 Random

1:1 Accuracy

Results

Performance results of various models on this benchmark

Model Name	1:1 Accuracy	Paper Title
MLP-2	92.26 ± 0.71	Revisiting Heterophily For Graph Neural Networks
GCNII*	88.52 ± 3.02	Simple and Deep Graph Convolutional Networks
Geom-GCN*	67.57	Geom-GCN: Geometric Graph Convolutional Networks
ACMII-GCN	95.08 ± 2.07	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-2	93.44 ± 2.54	Revisiting Heterophily For Graph Neural Networks
APPNP	91.18 ± 0.70	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
BernNet	93.12 ± 0.65	BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
ACM-GCNII	92.46 ± 1.97	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	96.56 ± 2	Revisiting Heterophily For Graph Neural Networks
NFGNN	94.03±0.82	Node-oriented Spectral Filtering for Graph Neural Networks
GCN+JK	80.66 ± 1.91	Revisiting Heterophily For Graph Neural Networks
SGC-2	81.31 ± 3.3	Simplifying Graph Convolutional Networks
GraphSAGE	79.03 ± 1.20	Inductive Representation Learning on Large Graphs
GCNII	82.46 ± 4.58	Simple and Deep Graph Convolutional Networks
ACM-GCN+	94.92 ± 2.79	Revisiting Heterophily For Graph Neural Networks
GPRGNN	92.92 ± 0.61	Adaptive Universal Generalized PageRank Graph Neural Network
ACM-SGC-1	93.61 ± 1.55	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-2	95.25 ± 1.55	Revisiting Heterophily For Graph Neural Networks
HH-GAT	80.54 ± 4.80	Half-Hop: A graph upsampling approach for slowing down message passing
GAT+JK	75.41 ± 7.18	Revisiting Heterophily For Graph Neural Networks

0 of 36 row(s) selected.