Node Classification On Non Homophilic 6

評価指標

1:1 Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	1:1 Accuracy	Paper Title
SGC-1	59.73±0.12	Simplifying Graph Convolutional Networks
ACM-GCN+	67.4±0.44	Revisiting Heterophily For Graph Neural Networks
GAT	61.09±0.77	Graph Attention Networks
ACMII-GCN	67.15±0.41	Revisiting Heterophily For Graph Neural Networks
GCNII	66.38±0.45	Simple and Deep Graph Convolutional Networks
ACM-GCN	67.01±0.38	Revisiting Heterophily For Graph Neural Networks
C&S(2hop)	64.52±0.62	Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
H2GCN	67.22±0.90	Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
GCN+JK	60.99±0.14	New Benchmarks for Learning on Non-Homophilous Graphs
GCN	62.23±0.53	Semi-Supervised Classification with Graph Convolutional Networks
LINK	57.71±0.36	New Benchmarks for Learning on Non-Homophilous Graphs
ACM-GCN++	67.3±0.48	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN+	67.44±0.31	Revisiting Heterophily For Graph Neural Networks
MixHop	66.80±0.58	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
FAGCN	66.86±0.53	Beyond Low-frequency Information in Graph Convolutional Networks
ACM-SGC-2	66.53±0.57	Revisiting Heterophily For Graph Neural Networks
LProp (2hop)	56.96±0.26	New Benchmarks for Learning on Non-Homophilous Graphs
GAT+JK	59.66±0.92	New Benchmarks for Learning on Non-Homophilous Graphs
APPNP	67.21±0.56	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
ACM-GCNII	66.39±0.56	Revisiting Heterophily For Graph Neural Networks

0 of 28 row(s) selected.