HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Graph Classification On Proteins

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper Title
HGP-SL84.91Hierarchical Graph Pooling with Structure Learning
rLap (unsupervised)84.3Randomized Schur Complement Views for Graph Contrastive Learning
TFGW ADJ (L=2)82.9Template based Graph Neural Network with Optimal Transport Distances
ESA (Edge set attention, no positional encodings)82.679±0.799An end-to-end attention-based approach for learning on graphs
DUGNN81.70%Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
MEWISPool80.71%Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
CIN++80.5CIN++: Enhancing Topological Message Passing
SAEPool80.36%Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization
UGT80.12 ±0.32Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
U2GNN (Unsupervised)80.01%Universal Graph Transformer Self-Attention Networks
sGIN78.97%Mutual Information Maximization in Graph Neural Networks
QS-CNNs (Quantum Walk)78.80%Quantum-based subgraph convolutional neural networks
WKPI-kmeans78.8%Learning metrics for persistence-based summaries and applications for graph classification
PIN78.8%Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
hGANet78.65%Graph Representation Learning via Hard and Channel-Wise Attention Networks
U2GNN78.53%Universal Graph Transformer Self-Attention Networks
DS-CNNs (Random Walk)78.35%Quantum-based subgraph convolutional neural networks
cGANet78.23%Graph Representation Learning via Hard and Channel-Wise Attention Networks
CAN78.2%Cell Attention Networks
GANet77.92%Graph Representation Learning via Hard and Channel-Wise Attention Networks
0 of 99 row(s) selected.