paper-with-me

Node Classification 벤치마크

Node Classification on pokec

7개 결과 · ⬇ CSV · JSON

Accuracy

81.55 82.78 84 85.23 86.46 2021-10 2026-11 LINKX — 82.04 (2021-10-27) GloGNN++ — 83.05 (2022-05-15) Dual-Net GNN — 81.55 (2023-01-25) OptBasisGNN — 82.83 (2023-02-24) Polynormer — 86.1 (2024-03-02) NeuralWalker — 86.46 (2024-06-05) GCN — 86.33 (2024-06-13) LINKX — 82.04 (2021-10-27) GloGNN++ — 83.05 (2022-05-15) Polynormer — 86.1 (2024-03-02) NeuralWalker — 86.46 (2024-06-05)
RankModel Accuracy PaperCodeYear
1 NeuralWalker 86.46 ± 0.09 Learning Long Range Dependencies on Graphs via Random Walks borgwardtlab/neuralwalker 2024
2 GCN 86.33 ± 0.17 Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification LUOyk1999/tunedGNN 2024
3 Polynormer 86.10±0.05 Polynormer: Polynomial-Expressive Graph Transformer in Linear Time cornell-zhang/Polynormer · cornell-zhang/polynormer 2024
4 GloGNN++ 83.05±0.07 Finding Global Homophily in Graph Neural Networks When Meeting Heterophily recklessronan/glognn 2022
5 OptBasisGNN 82.83±0.04 Graph Neural Networks with Learnable and Optimal Polynomial Bases yuziGuo/FarOptBasis 2023
6 LINKX 82.04±0.07 Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods cuai/non-homophily-large-scale · CUAI/Non-Homophily-Benchmarks · ivam-he/chebnetii · +2 2021
7 Dual-Net GNN 81.55±0.09 Feature Selection: Key to Enhance Node Classification with Graph Neural Networks sunilkmaurya/DualNetGNN_large 2023
1–7 / 7 페이지당 10 20 50 100