Graph Classification On Cifar10 100K

Accuracy (%)

Results

Performance results of various models on this benchmark

Model Name	Accuracy (%)	Paper Title	Repository
GAT	65.48	Graph Attention Networks
GRIT	76.468	Graph Inductive Biases in Transformers without Message Passing
GRED	76.853±0.185	Recurrent Distance Filtering for Graph Representation Learning
PNA	70.47	Principal Neighbourhood Aggregation for Graph Nets
Exphormer	74.754±0.194	Exphormer: Sparse Transformers for Graphs
ESA (Edge set attention, no positional encodings)	75.413±0.248	An end-to-end attention-based approach for learning on graphs	-
GraphSage	66.08	Inductive Representation Learning on Large Graphs
EGT	68.702	Global Self-Attention as a Replacement for Graph Convolution
MoNet	53.42	Geometric deep learning on graphs and manifolds using mixture model CNNs
GatedGCN	67.312	Benchmarking Graph Neural Networks
GraphGPS + HDSE	76.180±0.277	Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
EIGENFORMER	70.194	Graph Transformers without Positional Encodings	-
ARGNP	73.90	Automatic Relation-aware Graph Network Proliferation
GIN	53.28	How Powerful are Graph Neural Networks?
GatedGCN+	77.218 ± 0.381	Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence
TIGT	73.955	Topology-Informed Graph Transformer
NeuralWalker	80.027 ± 0.185	Learning Long Range Dependencies on Graphs via Random Walks
GatedGCN	69.37	Residual Gated Graph ConvNets
GPS	72.298	Recipe for a General, Powerful, Scalable Graph Transformer
DGN	72.84	Directional Graph Networks

0 of 20 row(s) selected.