HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Graph Classification On Collab

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper Title
U2GNN (Unsupervised)95.62%Universal Graph Transformer Self-Attention Networks
TFGW ADJ (L=2)84.3%Template based Graph Neural Network with Optimal Transport Distances
DUGNN84.20%Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
G_DenseNet83.16%When Work Matters: Transforming Classical Network Structures to Graph CNN
GFN81.50%Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
PPGN81.38%Provably Powerful Graph Networks
GFN-light81.34%Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
FactorGCN81.2%Factorizable Graph Convolutional Networks
GMT80.74%Accurate Learning of Graph Representations with Graph Multiset Pooling
sGIN80.71%Mutual Information Maximization in Graph Neural Networks
GCN80.6%Fast Graph Representation Learning with PyTorch Geometric
Self-supervised GraphMAE80.32%GraphMAE: Self-Supervised Masked Graph Autoencoders
GIN-080.2%How Powerful are Graph Neural Networks?
WEGL79.8%Wasserstein Embedding for Graph Learning
MEWISPool79.66%Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
CapsGNN79.62%Capsule Graph Neural Network
NDP79.1%Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
SEG-BERT78.42%Segmented Graph-Bert for Graph Instance Modeling
U2GNN77.84%Universal Graph Transformer Self-Attention Networks
R-GIN + PANDA77.8%PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
0 of 38 row(s) selected.