Node Classification On Penn94

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Dual-Net GNN	86.09±0.56	Feature Selection: Key to Enhance Node Classification with Graph Neural Networks	-
ACM-GCN++	86.08 ± 0.43	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	85.95 ± 0.26	Revisiting Heterophily For Graph Neural Networks
GloGNN++	85.74±0.42	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GloGNN	85.57 ± 0.35	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GNNMoE(GCN-like P)	85.11±0.39	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
ACM-GCN+	85.05 ± 0.19	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	84.95 ± 0.43	Revisiting Heterophily For Graph Neural Networks
DJ-GNN	84.84±0.34	Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters
NCGCN	84.74 ± 0.28	Clarify Confused Nodes via Separated Learning
LINKX	84.71 ± 0.52	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
GNNMoE(SAGE-like P)	84.05±0.37	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
MixHop	83.47 ± 0.71	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
GCNII	82.92 ± 0.59	Simple and Deep Graph Convolutional Networks
GCN	82.47 ± 0.27	Semi-Supervised Classification with Graph Convolutional Networks
GNNMoE(GAT-like P)	81.98±0.47	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
NCSAGE	81.77 ± 0.71	Clarify Confused Nodes via Separated Learning
GCNJK	81.63 ± 0.54	New Benchmarks for Learning on Non-Homophilous Graphs
GAT	81.53 ± 0.55	Graph Attention Networks
GPRGCN	81.38 ± 0.16	Adaptive Universal Generalized PageRank Graph Neural Network

0 of 32 row(s) selected.