Graph Classification On Enzymes

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
DAGCN	58.17%	DAGCN: Dual Attention Graph Convolutional Networks
UGT	67.22±3.92	Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
Multigraph ChebNet	61.7%	Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
ESA (Edge set attention, no positional encodings)	79.423±1.658	An end-to-end attention-based approach for learning on graphs	-
Evolution of Graph Classifiers	55.67	Evolution of Graph Classifiers
CapsGNN	54.67%	Capsule Graph Neural Network
TFGW SP (L=2)	75.1	Template based Graph Neural Network with Optimal Transport Distances
GATv2	77.987±2.112	How Attentive are Graph Attention Networks?
GCN	73.466±4.372	Semi-Supervised Classification with Graph Convolutional Networks
GIN + PANDA	46.2	PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
WEGL	60.5	Wasserstein Embedding for Graph Learning
DEMO-Net(weight)	27.2	DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
S2V (with 2 DiffPool)	63.33%	Hierarchical Graph Representation Learning with Differentiable Pooling
GFN-light	69.50%	Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
GDL-g (SP)	71.47	Online Graph Dictionary Learning
Fea2Fea-s2	48.5	Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks
ECC (5 scores)	52.67%	Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
DGK	53.43%	Deep Graph Kernels	-
GraphSAGE	58.2%	A Fair Comparison of Graph Neural Networks for Graph Classification
Norm-GN	73.33	A New Perspective on the Effects of Spectrum in Graph Neural Networks

0 of 53 row(s) selected.