Graph Classification On Mutag

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
Evolution of Graph Classifiers	100.00%	Evolution of Graph Classifiers
MEWISPool	96.66%	Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
TFGW ADJ (L=2)	96.4%	Template based Graph Neural Network with Optimal Transport Distances
GIUNet	95.7%	Graph isomorphism UNet
G_Inception	95.00%	When Work Matters: Transforming Classical Network Structures to Graph CNN
GIC	94.44%	Gaussian-Induced Convolution for Graphs
CIN++	94.4%	CIN++: Enhancing Topological Message Passing
sGIN	94.14%	Mutual Information Maximization in Graph Neural Networks
CAN	94.1%	Cell Attention Networks
Deep WL SGN(0,1,2)	93.68%	Subgraph Networks with Application to Structural Feature Space Expansion
QS-CNNs (Quantum Walk)	93.13%	Quantum-based subgraph convolutional neural networks
PATCHY-SAN	92.63%	Learning Convolutional Neural Networks for Graphs
DDGK	91.58%	DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
Graph-JEPA	91.25%	Graph-level Representation Learning with Joint-Embedding Predictive Architectures
GraphStar	91.2%	Graph Star Net for Generalized Multi-Task Learning
TREE-G	91.1%	TREE-G: Decision Trees Contesting Graph Neural Networks
SEG-BERT	90.85%	Segmented Graph-Bert for Graph Instance Modeling
GFN	90.84%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
PPGN	90.55%	Provably Powerful Graph Networks
GAT-GC (f-Scaled)	90.44%	Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation

0 of 74 row(s) selected.