Node Classification on Non-Homophilic (Heterophilic) Graphs 벤치마크

20% fixed splits)

26개 결과 · ⬇ CSV · JSON

1:1 Accuracy

Rank	Model	1:1 Accuracy	Paper	Code	Year
1	NLMLP	37.9 ± 1.3	Non-Local Graph Neural Networks	divelab/Non-Local-GNN	2020
2	O(d)-NSD	37.81 ± 1.15	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs	twitter-research/neural-sheaf-diffusion	2022
3	Gen-NSD	37.80 ± 1.22	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs	twitter-research/neural-sheaf-diffusion	2022
4	Diag-NSD	37.79 ± 1.01	Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs	twitter-research/neural-sheaf-diffusion	2022
5	GloGNN++	37.70 ± 1.40	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily	recklessronan/glognn	2022
6	GGCN	37.54 ± 1.56	Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks	yujun-yan/heterophily_and_oversmoothing	2021
7	GCNII	37.44 ± 1.30	Simple and Deep Graph Convolutional Networks	chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1	2020
8	GloGNN	37.35 ± 1.30	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily	recklessronan/glognn	2022
9	ACM-GCN++	37.31 ± 1.09	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
10	ACMII-GCN++	37.09 ± 1.32	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
11	Deformable GCN	37.07±0.79	Deformable Graph Convolutional Networks	mlvlab/DeformableGCN	2021
12	ACM-GCN	36.63 ± 0.84	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
13	WRGAT	36.53 ± 0.77	Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns	susheels/gnns-and-local-assortativity	2021
14	ACMII-GCN	36.31 ± 1.2	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
15	ACM-GCN+	36.26 ± 1.34	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
16	ACMII-GCN+	36.14 ± 1.44	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
17	LINKX	36.10 ± 1.55	Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods	cuai/non-homophily-large-scale · CUAI/Non-Homophily-Benchmarks · ivam-he/chebnetii · +2	2021
18	ACM-SGC-2	36.04 ± 0.83	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
19	H2GCN	35.70 ± 1.00	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs	GemsLab/H2GCN · GitEventhandler/H2GCN-PyTorch · sxwee/GNNsIMPL · +1	2020
20	ACM-SGC-1	35.49 ± 1.06	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022