Node Classification On Genius

1:1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
GESN	91.72 ± 0.08	Addressing Heterophily in Node Classification with Graph Echo State Networks
LINKX	-	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ACM-GCN++	-	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	-	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	-	Revisiting Heterophily For Graph Neural Networks
GPRGCN	-	Adaptive Universal Generalized PageRank Graph Neural Network
GCNJK	-	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACMII-GCN+	-	Revisiting Heterophily For Graph Neural Networks
GCNII	-	Simple and Deep Graph Convolutional Networks
LINK	-	New Benchmarks for Learning on Non-Homophilous Graphs
MixHop	-	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Dual-Net GNN	-	Feature Selection: Key to Enhance Node Classification with Graph Neural Networks
GloGNN	-	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
L Prop 2-hop	-	New Benchmarks for Learning on Non-Homophilous Graphs
L Prop 1-hop	-	New Benchmarks for Learning on Non-Homophilous Graphs
APPNP	-	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
SGC 2-hop	-	Simplifying Graph Convolutional Networks
GloGNN++	-	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
C&S 1-hop	-	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
SGC 1-hop	-	Simplifying Graph Convolutional Networks

0 of 26 row(s) selected.