Node Classification On Cora With Public Split

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
CoLinkDistMLP	81.19%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	-
AdaLanczosNet	80.4 ± 1.1	LanczosNet: Multi-Scale Deep Graph Convolutional Networks	-
GCN-TV	86.3%	Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals	-
ChebyNet	78.0%	Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering	-
GRAND	85.4 ± 0.4	Graph Random Neural Network for Semi-Supervised Learning on Graphs	-
GGNN	77.6%	Gated Graph Sequence Neural Networks	-
GAT	83.0 ± 0.7%	Graph Attention Networks	-
OGC	86.9%	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited	-
Snowball (linear)	83.26%	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks	-
GEM	83.05%	Graph Entropy Minimization for Semi-supervised Node Classification	-
CPF-ind-APPNP	85.3%	Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework	-
G-APPNP	84.31%	Pre-train and Learn: Preserve Global Information for Graph Neural Networks	-
GAT+PGN	83.26 ± 0.69%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs	-
LinkDistMLP	80.79%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	-
DCNN	79.7%	Diffusion-Convolutional Neural Networks	-
AIR-GCN	84.7%	GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction	-
SuperGAT MX	84.3%	How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision	-
GCN	85.1 ± 0.7	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification	-
GGCM	83.6%	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited	-
CoLinkDist	81.39%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages	-

0 of 36 row(s) selected.