Graph Classification On Nci1

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
SAGPool_g	74.06%	Self-Attention Graph Pooling	-
GIUNet	80.2%	Graph isomorphism UNet
TokenGT	76.740±2.054	Pure Transformers are Powerful Graph Learners	-
SF + RFC	75.2%	A Simple Baseline Algorithm for Graph Classification	-
GIC	84.08%	Gaussian-Induced Convolution for Graphs	-
DDGK	68.1%	DDGK: Learning Graph Representations for Deep Divergence Graph Kernels	-
CIN++	85.3%	CIN++: Enhancing Topological Message Passing	-
SAGPool_h	67.45%	Self-Attention Graph Pooling	-
WL-OA	86.1%	On Valid Optimal Assignment Kernels and Applications to Graph Classification	-
FGW wl h=4 sp	86.42%	Optimal Transport for structured data with application on graphs	-
GFN	83.65%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification	-
k-GNN	76.2%	Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks	-
WKPI-kmeans	87.2%	Learning metrics for persistence-based summaries and applications for graph classification	-
CAN	84.5%	Cell Attention Networks	-
ASAP	71.48	ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations	-
Fea2Fea-s3	74.9%	Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks	-
sGIN	83.85%	Mutual Information Maximization in Graph Neural Networks	-
graph2vec	73.22% ± 1.81%	graph2vec: Learning Distributed Representations of Graphs	-
WWL	85.75%	Wasserstein Weisfeiler-Lehman Graph Kernels	-
DAGCN	81.68%	DAGCN: Dual Attention Graph Convolutional Networks	-

0 of 67 row(s) selected.