Node Classification On Non Homophilic 4

평가 지표

1:1 Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	1:1 Accuracy	Paper Title
ACM-Snowball-2	68.51 ± 1.7	Revisiting Heterophily For Graph Neural Networks
ACM-Snowball-3	68.4 ± 2.05	Revisiting Heterophily For Graph Neural Networks
MixHop	36.28 ± 10.22	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
ACM-SGC-1	63.68 ± 1.62	Revisiting Heterophily For Graph Neural Networks
SGC-2	62.67 ± 2.41	Simplifying Graph Convolutional Networks
ACMII-Snowball-3	67.53 ± 2.83	Revisiting Heterophily For Graph Neural Networks
ACM-SGC-2	60.48 ± 1.55	Revisiting Heterophily For Graph Neural Networks
GPRGNN	67.48 ± 0.40	Adaptive Universal Generalized PageRank Graph Neural Network
GraphSAGE	62.15 ± 0.42	Inductive Representation Learning on Large Graphs
MLP-2	46.72 ± 0.46	Revisiting Heterophily For Graph Neural Networks
ACMII-GCN	68.38 ± 1.36	Revisiting Heterophily For Graph Neural Networks
GCN+JK	64.68 ± 2.85	Revisiting Heterophily For Graph Neural Networks
GAT+JK	68.14 ± 1.18	Revisiting Heterophily For Graph Neural Networks
ACM-GCNII	58.73 ± 2.52	Revisiting Heterophily For Graph Neural Networks
FAGCN	49.47 ± 2.84	Beyond Low-frequency Information in Graph Convolutional Networks
GCN	64.18 ± 2.62	Semi-Supervised Classification with Graph Convolutional Networks
SGC-1	64.86 ± 1.81	Simplifying Graph Convolutional Networks
BernNet	68.29 ± 1.58	BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
ACM-GCN++	75.23 ± 1.72	Revisiting Heterophily For Graph Neural Networks
GCNII*	62.8 ± 2.87	Simple and Deep Graph Convolutional Networks

0 of 32 row(s) selected.