Graph Classification On Cifar10 100K

Accuracy (%)

Results

Performance results of various models on this benchmark

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

0 of 20 row(s) selected.