HyperAI

Graph Classification On Enzymes

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Accuracy
Paper TitleRepository
DAGCN58.17%DAGCN: Dual Attention Graph Convolutional Networks
UGT67.22±3.92Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
Multigraph ChebNet61.7%Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
ESA (Edge set attention, no positional encodings)79.423±1.658An end-to-end attention-based approach for learning on graphs-
Evolution of Graph Classifiers55.67Evolution of Graph Classifiers
CapsGNN54.67%Capsule Graph Neural Network
TFGW SP (L=2)75.1Template based Graph Neural Network with Optimal Transport Distances
GATv277.987±2.112How Attentive are Graph Attention Networks?
GCN73.466±4.372Semi-Supervised Classification with Graph Convolutional Networks
GIN + PANDA46.2PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
WEGL60.5Wasserstein Embedding for Graph Learning
DEMO-Net(weight)27.2DEMO-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-light69.50%Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
GDL-g (SP)71.47Online Graph Dictionary Learning
Fea2Fea-s248.5Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks
ECC (5 scores)52.67%Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
DGK53.43%Deep Graph Kernels-
GraphSAGE58.2%A Fair Comparison of Graph Neural Networks for Graph Classification
Norm-GN73.33A New Perspective on the Effects of Spectrum in Graph Neural Networks
0 of 53 row(s) selected.