Graph Classification On Ptc

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
U2GNN (Unsupervised)	91.81%	Universal Graph Transformer Self-Attention Networks
GIUNet	85.7%	Graph isomorphism UNet
GIC	77.64%	Gaussian-Induced Convolution for Graphs
DUGNN	74.7%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
sGIN	73.56%	Mutual Information Maximization in Graph Neural Networks
UGraphEmb-F	73.56%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
G_DenseNet	73.24%	When Work Matters: Transforming Classical Network Structures to Graph CNN
CIN++	73.2%	CIN++: Enhancing Topological Message Passing
CAN	72.8%	Cell Attention Networks
UGraphEmb	72.54%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
TFGW ADJ (L=2)	72.4%	Template based Graph Neural Network with Optimal Transport Distances
DGA	71.24%	Discriminative Graph Autoencoder
U2GNN	69.63%	Universal Graph Transformer Self-Attention Networks
BC + Capsules	69%	Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations
SEG-BERT	68.86%	Segmented Graph-Bert for Graph Instance Modeling
Spec-GN	68.05%	A New Perspective on the Effects of Spectrum in Graph Neural Networks
WEGL	67.5%	Wasserstein Embedding for Graph Learning
WWL	66.31%	Wasserstein Weisfeiler-Lehman Graph Kernels
DropGIN	66.3%	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
PPGN	66.17%	Provably Powerful Graph Networks

0 of 37 row(s) selected.