Node Classification On Non Homophilic 15

Metriken

1:1 Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	1:1 Accuracy	Paper Title
MLP	60.92 ± 0.07	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
MixHop	65.64 ± 0.27	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
SGC 2-hop	59.94 ± 0.21	Simplifying Graph Convolutional Networks
ACM-GCN+	66.24 ± 0.24	Revisiting Heterophily For Graph Neural Networks
GESN	68.34 ± 0.86	Addressing Heterophily in Node Classification with Graph Echo State Networks
ACMII-GCN++	65.92 ± 0.14	Revisiting Heterophily For Graph Neural Networks
GloGNN++	66.34 ± 0.29	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
SGC 1-hop	58.97 ± 0.19	Simplifying Graph Convolutional Networks
ACM-GCN++	65.943 ± 0.284	Revisiting Heterophily For Graph Neural Networks
GCN	62.18 ± 0.26	Semi-Supervised Classification with Graph Convolutional Networks
GPRGCN	61.89 ± 0.29	Adaptive Universal Generalized PageRank Graph Neural Network
L Prop 1-hop	62.77 ± 0.24	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
APPNP	60.97 ± 0.10	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
GCNJK	63.45 ± 0.22	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
C&S 1-hop	64.86 ± 0.27	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
C&S 2-hop	65.02 ± 0.16	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
GloGNN	66.19 ± 0.29	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN	63.92 ± 0.19	Revisiting Heterophily For Graph Neural Networks
LINKX	66.06 ± 0.19	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ClenshawGCN	66.56 ± 0.28	Clenshaw Graph Neural Networks

0 of 26 row(s) selected.