ML Research Wiki / Benchmarks / Graph Classification / MNIST

MNIST

Graph Classification Benchmark

Performance Over Time

📊 Showing 13 results | 📏 Metric: Accuracy

Top Performing Models

Rank Model Paper Accuracy Date Code
1 CKGCN CKGConv: General Graph Convolution with Continuous Kernels 98.42 2024-04-21 📦 networkslab/ckgconv
2 EIGENFORMER Graph Transformers without Positional Encodings 98.36 2024-01-31 -
3 EGT Global Self-Attention as a Replacement for Graph Convolution 98.17 2021-08-07 📦 shamim-hussain/egt_pytorch 📦 shamim-hussain/egt 📦 shamim-hussain/egt_triangular
4 GRIT Graph Inductive Biases in Transformers without Message Passing 98.11 2023-05-27 📦 liamma/grit 📦 linusbao/MoSE
5 GPS Recipe for a General, Powerful, Scalable Graph Transformer 98.05 2022-05-25 📦 rampasek/GraphGPS 📦 hamed1375/exphormer 📦 graphcore/ogb-lsc-pcqm4mv2 📦 linusbao/MoSE
6 GatedGCN Benchmarking Graph Neural Networks 97.34 2020-03-02 📦 graphdeeplearning/benchmarking-gnns 📦 PaddlePaddle/PGL 📦 PaddlePaddle/PGL
7 ESA (Edge set attention, no positional encodings, tuned) An end-to-end attention-based approach for learning on graphs 0.00 2024-02-16 📦 davidbuterez/edge-set-attention
8 NeuralWalker Learning Long Range Dependencies on Graphs via Random Walks 0.00 2024-06-05 📦 borgwardtlab/neuralwalker
9 ESA (Edge set attention, no positional encodings) An end-to-end attention-based approach for learning on graphs 0.00 2024-02-16 📦 davidbuterez/edge-set-attention
10 GatedGCN+ Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence 0.00 2025-02-13 📦 LUOyk1999/GNNPlus

All Papers (13)

networkslab/ckgconv
shamim-hussain/egt_pytorch shamim-hussain/egt shamim-hussain/egt_triangular
liamma/grit linusbao/MoSE
rampasek/GraphGPS hamed1375/exphormer
graphdeeplearning/benchmarking-gnns PaddlePaddle/PGL

An end-to-end attention-based approach for learning on graphs

2024
ESA (Edge set attention, no positional encodings, tuned)
davidbuterez/edge-set-attention
borgwardtlab/neuralwalker

An end-to-end attention-based approach for learning on graphs

2024
ESA (Edge set attention, no positional encodings)
davidbuterez/edge-set-attention
LUOyk1999/GNNPlus
hamed1375/exphormer
LUOyk1999/GNNPlus
leemingo/tigt leemingo/cy2mixer