Graph Classification On Collab

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem 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
DUGNN	84.20%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
G_DenseNet	83.16%	When Work Matters: Transforming Classical Network Structures to Graph CNN
GFN	81.50%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
PPGN	81.38%	Provably Powerful Graph Networks
GFN-light	81.34%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
FactorGCN	81.2%	Factorizable Graph Convolutional Networks
GMT	80.74%	Accurate Learning of Graph Representations with Graph Multiset Pooling
sGIN	80.71%	Mutual Information Maximization in Graph Neural Networks
GCN	80.6%	Fast Graph Representation Learning with PyTorch Geometric
Self-supervised GraphMAE	80.32%	GraphMAE: Self-Supervised Masked Graph Autoencoders
GIN-0	80.2%	How Powerful are Graph Neural Networks?
WEGL	79.8%	Wasserstein Embedding for Graph Learning
MEWISPool	79.66%	Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
CapsGNN	79.62%	Capsule Graph Neural Network
NDP	79.1%	Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
SEG-BERT	78.42%	Segmented Graph-Bert for Graph Instance Modeling
U2GNN	77.84%	Universal Graph Transformer Self-Attention Networks
R-GIN + PANDA	77.8%	PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

0 of 38 row(s) selected.