OpenCodePapers

graph-classification-on-mnist

ClassificationGraph Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
An end-to-end attention-based approach for learning on graphs✓ Link98.917±0.020ESA (Edge set attention, no positional encodings, tuned)2024-02-16
Learning Long Range Dependencies on Graphs via Random Walks✓ Link98.760 ± 0.079NeuralWalker2024-06-05
An end-to-end attention-based approach for learning on graphs✓ Link98.753±0.041ESA (Edge set attention, no positional encodings)2024-02-16
Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence✓ Link98.712 ± 0.137GatedGCN+2025-02-13
CKGConv: General Graph Convolution with Continuous Kernels✓ Link98.423CKGCN2024-04-21
Exphormer: Sparse Transformers for Graphs✓ Link98.414±0.038Exphormer2023-03-10
Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence✓ Link98.382 ± 0.095GCN+2025-02-13
Graph Transformers without Positional Encodings98.362EIGENFORMER2024-01-31
Topology-Informed Graph Transformer✓ Link98.230±0.133TIGT2024-02-03
Global Self-Attention as a Replacement for Graph Convolution✓ Link98.173EGT2021-08-07
Graph Inductive Biases in Transformers without Message Passing✓ Link98.108GRIT2023-05-27
Recipe for a General, Powerful, Scalable Graph Transformer✓ Link98.05GPS2022-05-25
Benchmarking Graph Neural Networks✓ Link97.340GatedGCN2020-03-02
Check out how to contribute new results.