Graph Classification On Dd

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
U2GNN (Unsupervised)	95.67%	Universal Graph Transformer Self-Attention Networks
MEWISPool	84.33%	Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
ESA (Edge set attention, no positional encodings)	83.529±1.743	An end-to-end attention-based approach for learning on graphs
DDGK	83.14%	DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
Graph U-Nets	82.43%	Graph U-Nets
DUGNN	82.40%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
S2V (with 2 DiffPool)	82.07%	Hierarchical Graph Representation Learning with Differentiable Pooling
WKPI-kmeans	82.0%	Learning metrics for persistence-based summaries and applications for graph classification
hGANet	81.71%	Graph Representation Learning via Hard and Channel-Wise Attention Networks
HGP-SL	80.96%	Hierarchical Graph Pooling with Structure Learning
SEAL-SAGE	80.88%	Semi-Supervised Graph Classification: A Hierarchical Graph Perspective
GNN (DiffPool)	80.64%	Hierarchical Graph Representation Learning with Differentiable Pooling
NERO	80.45%	Relation order histograms as a network embedding tool	-
U2GNN	80.23%	Universal Graph Transformer Self-Attention Networks
WWL	79.69%	Wasserstein Weisfeiler-Lehman Graph Kernels
GraphStar	79.60%	Graph Star Net for Generalized Multi-Task Learning
DGCNN	79.37%	An End-to-End Deep Learning Architecture for Graph Classification	-
PNA	78.992±4.407	Principal Neighbourhood Aggregation for Graph Nets
Propagation kernels (pk)	78.8%	Propagation kernels: efficient graph kernels from propagated information	-
GFN	78.78%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

0 of 52 row(s) selected.