Graph Classification On Ptc

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy	Paper Title	Repository
U2GNN (Unsupervised)	91.81%	Universal Graph Transformer Self-Attention Networks	-
U2GNN	69.63%	Universal Graph Transformer Self-Attention Networks	-
δ-2-LWL	62.70%	Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings	-
DGA	71.24%	Discriminative Graph Autoencoder	-
WWL	66.31%	Wasserstein Weisfeiler-Lehman Graph Kernels	-
DGCNN	65.43%	DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model	-
Deep WL SGN(0,1,2)	65.88%	Subgraph Networks with Application to Structural Feature Space Expansion	-
TFGW ADJ (L=2)	72.4%	Template based Graph Neural Network with Optimal Transport Distances	-
DDGK	63.14%	DDGK: Learning Graph Representations for Deep Divergence Graph Kernels	-
DUGNN	74.7%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning	-
UGraphEmb	72.54%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity	-
Spec-GN	68.05%	A New Perspective on the Effects of Spectrum in Graph Neural Networks	-
SPI-GCN	56.41%	SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network	-
SF + RFC	62.8%	A Simple Baseline Algorithm for Graph Classification	-
TREE-G	59.1%	TREE-G: Decision Trees Contesting Graph Neural Networks	-
GIUNet	85.7%	Graph isomorphism UNet
cGANet	63.53%	Graph Representation Learning via Hard and Channel-Wise Attention Networks	-
graph2vec	60.17% ± 6.86%	graph2vec: Learning Distributed Representations of Graphs	-
CAN	72.8%	Cell Attention Networks	-
CIN++	73.2%	CIN++: Enhancing Topological Message Passing	-

0 of 37 row(s) selected.