HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Node Classification On Cora

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
SSP90.16% ± 0.59%Optimization of Graph Neural Networks with Natural Gradient Descent
SplineCNN89.48% ± 0.31%SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
ACMII-Snowball-389.36% ± 1.26%Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
ACMII-GCN88.95% ± 1.04%Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
ACM-Snowball-288.83% ± 1.49%Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
UGT88.74±0.6%Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
GAT + SWA88.66 ± 1.38%The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ACM-GCN88.62% ± 1.22%Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
GCN-LPA88.5% ± 1.5%Unifying Graph Convolutional Neural Networks and Label Propagation
LinkDist88.24%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CNMPGNN88.20±1.22%CN-Motifs Perceptive Graph Neural Networks
CoLinkDist87.89%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
3ference87.78%Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
LinkDistMLP87.58%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CoLinkDistMLP87.54%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
AS-GCN87.44% ± 0.0034%Adaptive Sampling Towards Fast Graph Representation Learning
CGT87.10±1.53Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
Cleora86.80%Cleora: A Simple, Strong and Scalable Graph Embedding Scheme
NodeNet86.80%NodeNet: A Graph Regularised Neural Network for Node Classification
DFNet-ATT86% ± 0.4%DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
0 of 72 row(s) selected.
Node Classification On Cora | SOTA | HyperAI超神経