Graph Classification on MUTAG

148개 결과 · ⬇ CSV · JSON

Accuracy

Rank	Model	Accuracy	Accuracy (10-fold)	Mean Accuracy	Accuracy (10 fold)	Extra Training Data	Paper	Code	Year
1	Evolution of Graph Classifiers	100.00%	100	–	–		Evolution of Graph Classifiers	rohand24/GraphCNN_evolution	2019
2	MEWISPool	96.66%	–	–	–		Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks	mewispool/mewispool	2021
3	TFGW ADJ (L=2)	96.4%	–	–	–		Template based Graph Neural Network with Optimal Transport Distances	cedricvincentcuaz/TFGW	2022
4	GIUNet	95.7%	–	–	–		Graph isomorphism UNet	aramiracle/GIUNet	2023
5	G_Inception	95.00%	–	–	–		When Work Matters: Transforming Classical Network Structures to Graph CNN		2018
6	GIC	94.44%	–	–	–		Gaussian-Induced Convolution for Graphs		2018
7	CIN++	94.4%	–	–	–		CIN++: Enhancing Topological Message Passing	twitter-research/cwn	2023
8	sGIN	94.14%	–	–	–	✓	Mutual Information Maximization in Graph Neural Networks	CODE-SUBMIT/Graph_Neighborhood_1 · CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network	2019
9	CAN	94.1%	–	–	–		Cell Attention Networks	lrnzgiusti/can	2022
10	Deep WL SGN(0,1,2)	93.68%	–	–	–		Subgraph Networks with Application to Structural Feature Space Expansion		2019
11	QS-CNNs (Quantum Walk)	93.13%	93.13	–	–		Quantum-based subgraph convolutional neural networks		2019
12	PATCHY-SAN	92.63%	–	–	–		Learning Convolutional Neural Networks for Graphs	tvayer/PSCN · CielAl/PatchySan	2016
13	DDGK	91.58%	–	–	–		DDGK: Learning Graph Representations for Deep Divergence Graph Kernels	google-research/google-research	2019
14	Graph-JEPA	91.25%	–	–	–		Graph-level Representation Learning with Joint-Embedding Predictive Architectures	geriskenderi/graph-jepa	2023
15	GraphStar	91.2%	–	–	–		Graph Star Net for Generalized Multi-Task Learning	graph-star-team/graph_star	2019
16	TREE-G	91.1%	–	–	–		TREE-G: Decision Trees Contesting Graph Neural Networks	mayabechlerspeicher/tree-g	2022
17	SEG-BERT	90.85%	–	–	–		Segmented Graph-Bert for Graph Instance Modeling	jwzhanggy/SEG-BERT	2020
18	GFN	90.84%	–	–	–		Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification	chentingpc/gfn	2019
19	PPGN	90.55%	–	–	–		Provably Powerful Graph Networks	hadarser/ProvablyPowerfulGraphNetworks_torch · hadarser/ProvablyPowerfulGraphNetworks	2019
20	GAT-GC (f-Scaled)	90.44%	–	–	–	✓	Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation	zetayue/CPA	2019