HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Node Classification On Cora 60 20 20 Random

المقاييس

1:1 Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
1:1 Accuracy
Paper TitleRepository
GPRGNN79.51 ± 0.36Adaptive Universal Generalized PageRank Graph Neural Network
GCNII88.98 ± 1.33Simple and Deep Graph Convolutional Networks
GNNDLD92.99 ±0.9GNNDLD: Graph Neural Network with Directional Label Distribution-
Geom-GCN*85.27Geom-GCN: Geometric Graph Convolutional Networks
ACM-GCN+89.75 ± 1.16Revisiting Heterophily For Graph Neural Networks
ACM-GCNII*89.00 ± 1.35Revisiting Heterophily For Graph Neural Networks
ACM-SGC-287.64 ± 0.99Revisiting Heterophily For Graph Neural Networks
BernNet88.52 ± 0.95BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
SGC-185.12 ± 1.64Simplifying Graph Convolutional Networks
H2GCN87.52 ± 0.61Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
ACM-GCN++89.33 ± 0.81Revisiting Heterophily For Graph Neural Networks
MLP-276.44 ± 0.30Revisiting Heterophily For Graph Neural Networks
ACMII-GCN++89.47 ± 1.08Revisiting Heterophily For Graph Neural Networks
ACMII-Snowball-389.36 ± 1.26Revisiting Heterophily For Graph Neural Networks
GCN+JK86.90 ± 1.51007: Democratically Finding The Cause of Packet Drops
ACMII-GCN89.00 ± 0.72Revisiting Heterophily For Graph Neural Networks
GCNII*88.93 ± 1.37Simple and Deep Graph Convolutional Networks
Snowball-288.64 ± 1.15Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
ACM-SGC-186.63 ± 1.13Revisiting Heterophily For Graph Neural Networks
Snowball-389.33 ± 1.3Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
0 of 33 row(s) selected.