Node Classification On Non Homophilic 1

评估指标

1:1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	1:1 Accuracy	Paper Title
GAT	71.01 ± 4.66	Graph Attention Networks
MixHop	77.25 ± 7.80	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
ACM-GCNII	94.63 ± 2.96	Revisiting Heterophily For Graph Neural Networks
Snowball-2	74.88 ± 3.42	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
GraphSAGE	64.85 ± 5.14	Inductive Representation Learning on Large Graphs
H2GCN	87.5 ± 1.77	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
ACMII-Snowball-2	96.63 ± 2.24	Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-3	97.00 ± 2.63	Revisiting Heterophily For Graph Neural Networks
GCN+JK	62.50 ± 15.75	Revisiting Heterophily For Graph Neural Networks
GPRGNN	93.75 ± 2.37	Adaptive Universal Generalized PageRank Graph Neural Network
ACM-Snowball-2	96.38 ± 2.59	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-1	93.25 ± 2.92	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	96.75 ± 1.79	Revisiting Heterophily For Graph Neural Networks
Geom-GCN*	64.12	Geom-GCN: Geometric Graph Convolutional Networks
ACM-SGC-2	94.00 ± 2.61	Revisiting Heterophily For Graph Neural Networks
MLP-2	93.87 ± 3.33	New Benchmarks for Learning on Non-Homophilous Graphs
Snowball-3	69.5 ± 5.01	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
APPNP	92.00 ± 3.59	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
ACM-GCNII*	94.37 ± 2.81	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++	97.13 ± 1.68	Revisiting Heterophily For Graph Neural Networks

0 of 32 row(s) selected.