Node Classification On Non Homophilic 11

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

		Paper Title
ScaleNet	80.1±1.5	Scale Invariance of Graph Neural Networks
Dir-GNN	79.71±1.26	Edge Directionality Improves Learning on Heterophilic Graphs
GESN	77.05 ± 1.24	Addressing Heterophily in Node Classification with Graph Echo State Networks
ACMII-GCN++	74.76 ± 2.2	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	74.56 ± 2.08	Revisiting Heterophily For Graph Neural Networks
ACM-GCN+	74.47 ± 1.84	Revisiting Heterophily For Graph Neural Networks
ACM-GCN++	74.41 ± 1.49	Revisiting Heterophily For Graph Neural Networks
GloGNN++	71.21 ± 1.84	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GGCN	71.14 ±1.84	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Deformable GCN	70.90 ±1.12	Deformable Graph Convolutional Networks
NLGCN	70.1 ± 2.9	Non-Local Graph Neural Networks
GloGNN	69.78 ± 2.42	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACM-GCN	69.14 ± 1.91	Revisiting Heterophily For Graph Neural Networks
Diag-NSD	68.68 ± 1.73	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACMII-GCN	68.46 ± 1.7	Revisiting Heterophily For Graph Neural Networks
LINKX	68.42 ± 1.38	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
O(d)-NSD	68.04 ± 1.58	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Gen-NSD	67.93 ± 1.58	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
NLGAT	65.7 ± 1.4	Non-Local Graph Neural Networks
WRGAT	65.24 ± 0.87	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

0 of 29 row(s) selected.