HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Node Classification On Non Homophilic 15

Metrics

1:1 Accuracy

Results

Performance results of various models on this benchmark

Model Name
1:1 Accuracy
Paper TitleRepository
MLP60.92 ± 0.07Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
MixHop65.64 ± 0.27MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
SGC 2-hop59.94 ± 0.21Simplifying Graph Convolutional Networks
ACM-GCN+66.24 ± 0.24Revisiting Heterophily For Graph Neural Networks
GESN68.34 ± 0.86Addressing Heterophily in Node Classification with Graph Echo State Networks
ACMII-GCN++65.92 ± 0.14Revisiting Heterophily For Graph Neural Networks
GloGNN++66.34 ± 0.29Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
SGC 1-hop58.97 ± 0.19Simplifying Graph Convolutional Networks
ACM-GCN++65.943 ± 0.284Revisiting Heterophily For Graph Neural Networks
GCN62.18 ± 0.26Semi-Supervised Classification with Graph Convolutional Networks
GPRGCN61.89 ± 0.29Adaptive Universal Generalized PageRank Graph Neural Network
L Prop 1-hop62.77 ± 0.24Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
APPNP60.97 ± 0.10Predict then Propagate: Graph Neural Networks meet Personalized PageRank
GCNJK63.45 ± 0.22Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
C&S 1-hop 64.86 ± 0.27Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
C&S 2-hop65.02 ± 0.16Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
GloGNN66.19 ± 0.29Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN63.92 ± 0.19Revisiting Heterophily For Graph Neural Networks
LINKX66.06 ± 0.19Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
ClenshawGCN66.56 ± 0.28Clenshaw Graph Neural Networks
0 of 26 row(s) selected.