Node Classification On Non Homophilic 12

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
ACM-GCN	55.19 ± 1.49	Revisiting Heterophily For Graph Neural Networks
LINKX	61.81 ± 1.80	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Deformable GCN	62.56 ± 1.31	Deformable Graph Convolutional Networks
ACM-GCN++	67.06 ± 1.66	Revisiting Heterophily For Graph Neural Networks
GESN	73.56 ± 1.62	Addressing Heterophily in Node Classification with Graph Echo State Networks
ScaleNet	76.0±2.0	Scale Invariance of Graph Neural Networks
Gen-NSD	53.17 ± 1.31	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GGCN	55.17 ± 1.58	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
WRGAT	48.85 ± 0.78	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
GloGNN++	57.88 ± 1.76	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
NLMLP	33.7 ± 1.5	Non-Local Graph Neural Networks
ACMII-GCN	51.8 ± 1.5	Revisiting Heterophily For Graph Neural Networks
GPRGCN	46.31 ± 2.46	Adaptive Universal Generalized PageRank Graph Neural Network
GCNII	38.47 ± 1.58	Simple and Deep Graph Convolutional Networks
O(d)-NSD	56.34 ± 1.32	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACM-GCN+	66.98 ± 1.71	Revisiting Heterophily For Graph Neural Networks
NLGCN	59.0 ± 1.2	Non-Local Graph Neural Networks
GloGNN	57.54 ± 1.39	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Dir-GNN	75.31±1.92	Edge Directionality Improves Learning on Heterophilic Graphs
ACM-SGC-2	40.02 ± 0.96	Revisiting Heterophily For Graph Neural Networks

0 of 29 row(s) selected.