Node Classification On Squirrel 60 20 20

المقاييس

1:1 Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	1:1 Accuracy	Paper Title	Repository
GCN	44.76 ± 1.39	Semi-Supervised Classification with Graph Convolutional Networks	-
ACM-SGC-2	40.91 ± 1.39	Revisiting Heterophily For Graph Neural Networks	-
GraphSAGE	41.26 ± 0.26	Inductive Representation Learning on Large Graphs	-
ACM-SGC-1	46.4 ± 1.13	Revisiting Heterophily For Graph Neural Networks	-
GAT	42.72 ± 0.33	Graph Attention Networks	-
ACM-Snowball-3	55.73 ± 2.39	Revisiting Heterophily For Graph Neural Networks	-
NFGNN	58.9±0.35	Node-oriented Spectral Filtering for Graph Neural Networks	-
ACM-Snowball-2	55.97 ± 2.03	Revisiting Heterophily For Graph Neural Networks	-
HH-GCN	47.19 ± 1.21	Half-Hop: A graph upsampling approach for slowing down message passing	-
GPRGNN	49.93 ± 0.53	Adaptive Universal Generalized PageRank Graph Neural Network	-
SGC-2	41.25 ± 1.4	Simplifying Graph Convolutional Networks	-
ACMII-GCN++	69.98 ± 1.53	Revisiting Heterophily For Graph Neural Networks	-
Snowball-2	47.88 ± 1.23	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks	-
GNNDLD	77.72±0.84	GNNDLD: Graph Neural Network with Directional Label Distribution	-
GCN+JK	53.40 ± 1.90	Revisiting Heterophily For Graph Neural Networks	-
APPNP	34.77 ± 0.34	Predict then Propagate: Graph Neural Networks meet Personalized PageRank	-
GAT+JK	52.28 ± 3.61	Revisiting Heterophily For Graph Neural Networks	-
BernNet	51.35 ± 0.73	BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation	-
MLP-2	31.28 ± 0.27	Revisiting Heterophily For Graph Neural Networks	-
HH-GraphSAGE	45.25 ± 1.52	Half-Hop: A graph upsampling approach for slowing down message passing	-

0 of 37 row(s) selected.