Graph Classification On Enzymes

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
ESA (Edge set attention, no positional encodings)	79.423±1.658	An end-to-end attention-based approach for learning on graphs
GraphGPS	78.667±4.625	Recipe for a General, Powerful, Scalable Graph Transformer
GAT	78.611±1.556	Graph Attention Networks
DSGCN-allfeat	78.39	Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
GATv2	77.987±2.112	How Attentive are Graph Attention Networks?
TFGW SP (L=2)	75.1	Template based Graph Neural Network with Optimal Transport Distances
GCN	73.466±4.372	Semi-Supervised Classification with Graph Convolutional Networks
Norm-GN	73.33	A New Perspective on the Effects of Spectrum in Graph Neural Networks
PNA	73.021±2.512	Principal Neighbourhood Aggregation for Graph Nets
GDL-g (SP)	71.47	Online Graph Dictionary Learning
FGW sp	71.00%	Optimal Transport for structured data with application on graphs
GFN	70.17%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
GIUNet	70%	Graph isomorphism UNet
GFN-light	69.50%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
HGP-SL	68.79	Hierarchical Graph Pooling with Structure Learning
GIN	68.303±4.170	How Powerful are Graph Neural Networks?
G_Inception	67.50%	When Work Matters: Transforming Classical Network Structures to Graph CNN
DUGNN	67.30%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
UGT	67.22±3.92	Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
GraphStar	67.1%	Graph Star Net for Generalized Multi-Task Learning

0 of 53 row(s) selected.

Command Palette

Graph Classification On Enzymes

Metrics

Results