Graph Classification On Mutag

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy	Paper Title	Repository
GAP-Layer (Ncut)	86.9%	DiffWire: Inductive Graph Rewiring via the Lovász Bound	-
VRGC	86.3%	Variational Recurrent Neural Networks for Graph Classification	-
GDL-g (SP)	87.09%	Online Graph Dictionary Learning	-
GIN-0	89.4%	How Powerful are Graph Neural Networks?	-
WKPI-kcenters	87.5%	Learning metrics for persistence-based summaries and applications for graph classification	-
FGW wl h=2 sp	86.42%	Optimal Transport for structured data with application on graphs	-
ApproxRepSet	86.33%	Rep the Set: Neural Networks for Learning Set Representations	-
Function Space Pooling	83.3%	IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification	-
NDP	84.7%	Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling	-
PATCHY-SAN	92.63%	Learning Convolutional Neural Networks for Graphs	-
Path up to length h	88.47%	Graph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons
SPI-GCN	84.40%	SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network	-
DGCNN	85.83%	An End-to-End Deep Learning Architecture for Graph Classification
P-WL-C	-	A Persistent Weisfeiler–Lehman Procedure for Graph Classification	-
edGNN (max)	88.8%	edGNN: a Simple and Powerful GNN for Directed Labeled Graphs	-
hGANet	90.00%	Graph Representation Learning via Hard and Channel-Wise Attention Networks	-
CT-Layer	87.58%	DiffWire: Inductive Graph Rewiring via the Lovász Bound	-
U2GNN (Unsupervised)	88.47%	Universal Graph Transformer Self-Attention Networks	-
R-GIN + PANDA	88.2%	PANDA: Expanded Width-Aware Message Passing Beyond Rewiring	-
k-GNN	86.1%	Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks	-

0 of 74 row(s) selected.