HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Graph Classification On Nci1

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper Title
TFGW ADJ (L=2)88.1%Template based Graph Neural Network with Optimal Transport Distances
ESA (Edge set attention, no positional encodings)87.835±0.644An end-to-end attention-based approach for learning on graphs
WKPI-kmeans87.2%Learning metrics for persistence-based summaries and applications for graph classification
FGW wl h=4 sp86.42%Optimal Transport for structured data with application on graphs
WL-OA86.1%On Valid Optimal Assignment Kernels and Applications to Graph Classification
WL-OA Kernel86.1%Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
FGW wl h=2 sp85.82%Optimal Transport for structured data with application on graphs
WWL85.75%Wasserstein Weisfeiler-Lehman Graph Kernels
DUGNN85.50%Learning Universal Adversarial Perturbations with Generative Models
δ-2-LWL85.5%Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
CIN++85.3%CIN++: Enhancing Topological Message Passing
CORE-WL85.12%Graph Kernels: A Survey
GraphGPS85.110±1.423Recipe for a General, Powerful, Scalable Graph Transformer
GAT85.109±1.107Graph Attention Networks
PIN85.1%Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
PNA84.964±1.391Principal Neighbourhood Aggregation for Graph Nets
Norm-GN84.87%A New Perspective on the Effects of Spectrum in Graph Neural Networks
GIN84.818±0.936How Powerful are Graph Neural Networks?
CAN84.5%Cell Attention Networks
Propagation kernels (pk)84.5%Propagation kernels: efficient graph kernels from propagated information
0 of 67 row(s) selected.