HyperAIHyperAI

Command Palette

Search for a command to run...

Plateforme

Node Classification On Citeseer 48 32 20

Métriques

1:1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper Title
Geom-GCN78.02 ± 1.15Geom-GCN: Geometric Graph Convolutional Networks
ACM-GCN+77.67 ± 1.19Revisiting Heterophily For Graph Neural Networks
ACM-GCN++77.46 ± 1.65Revisiting Heterophily For Graph Neural Networks
GloGNN77.41 ± 1.65Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
GCNII77.33 ± 1.48Simple and Deep Graph Convolutional Networks
GloGNN++77.22 ± 1.78Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
ACMII-GCN+77.2 ± 1.61Revisiting Heterophily For Graph Neural Networks
ACMII-GCN77.15 ± 1.45Revisiting Heterophily For Graph Neural Networks
Diag-NSD77.14 ± 1.85Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
GGCN77.14 ± 1.45Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
GPRGCN77.13 ± 1.67Adaptive Universal Generalized PageRank Graph Neural Network
ACMII-GCN++77.12 ± 1.58Revisiting Heterophily For Graph Neural Networks
H2GCN77.11 ± 1.57Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
FAGCN77.07 ± 2.05Beyond Low-frequency Information in Graph Convolutional Networks
WRGAT76.81 ± 1.89Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
ACM-SGC-176.73 ± 1.59Revisiting Heterophily For Graph Neural Networks
O(d)-NSD76.70 ± 1.57Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
ACM-SGC-276.59 ± 1.69Revisiting Heterophily For Graph Neural Networks
Gen-NSD76.32 ± 1.65Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
MixHop76.26 ± 1.33MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
0 of 26 row(s) selected.