Graph Classification On Nci109

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
WKPI-kcenters	87.3	Learning metrics for persistence-based summaries and applications for graph classification
WL-OA	86.3	On Valid Optimal Assignment Kernels and Applications to Graph Classification
ESA (Edge set attention, no positional encodings)	84.976±0.551	An end-to-end attention-based approach for learning on graphs
δ-2-LWL	84.7	Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
CIN++	84.5	CIN++: Enhancing Topological Message Passing
GIN	84.155±0.812	How Powerful are Graph Neural Networks?
PIN	84.0	Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
DropGIN	83.961±1.141	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Spec-GN	83.62	A New Perspective on the Effects of Spectrum in Graph Neural Networks
CAN	83.6	Cell Attention Networks
Propagation kernels (pk)	83.5	Propagation kernels: efficient graph kernels from propagated information
PNA	83.382±1.045	Principal Neighbourhood Aggregation for Graph Nets
GCN	83.140±1.248	Semi-Supervised Classification with Graph Convolutional Networks
GATv2	83.092±0.764	How Attentive are Graph Attention Networks?
GIC	82.86	Gaussian-Induced Convolution for Graphs
GAT	82.560±0.601	Graph Attention Networks
PPGN	82.23	Provably Powerful Graph Networks
ECC (5 scores)	82.14	Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
Multigraph ChebNet	82.0	Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
GraphGPS	81.256±0.501	Recipe for a General, Powerful, Scalable Graph Transformer

0 of 37 row(s) selected.

Command Palette

Graph Classification On Nci109

Metriken

Ergebnisse