Node Classification on Non-Homophilic (Heterophilic) Graphs 벤치마크

20% random splits)

32개 결과 · ⬇ CSV · JSON

1:1 Accuracy

Rank	Model	1:1 Accuracy	Paper	Code	Year
21	SGC-1	83.28 ± 5.43	Simplifying Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · dmlc/dgl · +4	2019
22	GCN	83.11 ± 3.2	Semi-Supervised Classification with Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · tkipf/gcn · +52	2016
23	Snowball-2	83.11 ± 3.2	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks	PwnerHarry/Stronger_GCN	2019
24	Snowball-3	83.11 ± 3.2	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks	PwnerHarry/Stronger_GCN	2019
25	GCNII	82.46 ± 4.58	Simple and Deep Graph Convolutional Networks	chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1	2020
26	SGC-2	81.31 ± 3.3	Simplifying Graph Convolutional Networks	dmlc/dgl · dmlc/dgl · dmlc/dgl · +4	2019
27	GCN+JK	80.66 ± 1.91	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
28	GraphSAGE	79.03 ± 1.20	Inductive Representation Learning on Large Graphs	pyg-team/pytorch_geometric · dmlc/dgl · dmlc/dgl · +17	2017
29	GAT	78.87 ± 0.86	Graph Attention Networks	labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90	2017
30	MixHop	76.39 ± 7.66	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing	dmlc/dgl · benedekrozemberczki/MixHop-and-N-GCN · samihaija/mixhop	2019
31	GAT+JK	75.41 ± 7.18	Revisiting Heterophily For Graph Neural Networks	SitaoLuan/ACM-GNN	2022
32	Geom-GCN*	67.57	Geom-GCN: Geometric Graph Convolutional Networks	bingzhewei/geom-gcn · graphdml-uiuc-jlu/geom-gcn · alexfanjn/geomgcn_pyg · +1	2020