paper-with-me

Graph Classification 벤치마크

Graph Classification on MNIST

26개 결과 · ⬇ CSV · JSON

Accuracy

97.34 97.73 98.13 98.52 98.92 2020-03 2026-11 GatedGCN — 97.34 (2020-03-02) GatedGCN — 97.34 (2020-03-02) EGT — 98.173 (2021-08-07) EGT — 98.173 (2021-08-07) GPS — 98.05 (2022-05-25) GPS — 98.05 (2022-05-25) Exphormer — 98.414 (2023-03-10) Exphormer — 98.414 (2023-03-10) GRIT — 98.108 (2023-05-27) GRIT — 98.108 (2023-05-27) EIGENFORMER — 98.362 (2024-01-31) EIGENFORMER — 98.362 (2024-01-31) TIGT — 98.23 (2024-02-03) TIGT — 98.23 (2024-02-03) ESA (Edge set attention, no positional encodings, tuned) — 98.917 (2024-02-16) ESA (Edge set attention, no positional encodings) — 98.753 (2024-02-16) ESA (Edge set attention, no positional encodings, tuned) — 98.917 (2024-02-16) ESA (Edge set attention, no positional encodings) — 98.753 (2024-02-16) CKGCN — 98.423 (2024-04-21) CKGCN — 98.423 (2024-04-21) NeuralWalker — 98.76 (2024-06-05) NeuralWalker — 98.76 (2024-06-05) GatedGCN+ — 98.712 (2025-02-13) GCN+ — 98.382 (2025-02-13) GatedGCN+ — 98.712 (2025-02-13) GCN+ — 98.382 (2025-02-13) GatedGCN — 97.34 (2020-03-02) EGT — 98.173 (2021-08-07) Exphormer — 98.414 (2023-03-10) ESA (Edge set attention, no positional encodings, tuned) — 98.917 (2024-02-16)
RankModel Accuracy PaperCodeYear
1 ESA (Edge set attention, no positional encodings, tuned) 98.917±0.020 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
2 NeuralWalker 98.760 ± 0.079 Learning Long Range Dependencies on Graphs via Random Walks borgwardtlab/neuralwalker 2024
3 ESA (Edge set attention, no positional encodings) 98.753±0.041 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
4 GatedGCN+ 98.712 ± 0.137 Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
5 CKGCN 98.423 CKGConv: General Graph Convolution with Continuous Kernels networkslab/ckgconv 2024
6 Exphormer 98.414±0.038 Exphormer: Sparse Transformers for Graphs hamed1375/exphormer 2023
7 GCN+ 98.382 ± 0.095 Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
8 EIGENFORMER 98.362 Graph Transformers without Positional Encodings 2024
9 TIGT 98.230±0.133 Topology-Informed Graph Transformer leemingo/tigt · leemingo/cy2mixer 2024
10 EGT 98.173 Global Self-Attention as a Replacement for Graph Convolution shamim-hussain/egt_pytorch · shamim-hussain/egt · shamim-hussain/egt_triangular 2021
11 GRIT 98.108 Graph Inductive Biases in Transformers without Message Passing liamma/grit · linusbao/MoSE 2023
12 GPS 98.05 Recipe for a General, Powerful, Scalable Graph Transformer rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1 2022
13 GatedGCN 97.340 Benchmarking Graph Neural Networks graphdeeplearning/benchmarking-gnns · PaddlePaddle/PGL · PaddlePaddle/PGL · +12 2020
14 ESA (Edge set attention, no positional encodings, tuned) 98.917±0.020 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
15 NeuralWalker 98.760 ± 0.079 Learning Long Range Dependencies on Graphs via Random Walks borgwardtlab/neuralwalker 2024
16 ESA (Edge set attention, no positional encodings) 98.753±0.041 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
17 GatedGCN+ 98.712 ± 0.137 Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
18 CKGCN 98.423 CKGConv: General Graph Convolution with Continuous Kernels networkslab/ckgconv 2024
19 Exphormer 98.414±0.038 Exphormer: Sparse Transformers for Graphs hamed1375/exphormer 2023
20 GCN+ 98.382 ± 0.095 Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
1–20 / 26 다음 → 페이지당 10 20 50 100