paper-with-me

Node Classification 벤치마크

Node Classification on Cora: fixed 20 node per class

9개 결과 · ⬇ CSV · JSON

Accuracy

81.7 82.33 82.95 83.58 84.2 2018-09 2026-09 SEGCN — 83.5 (2018-09-26) LDS-GNN — 84.1 (2019-03-28) DSGCN — 84.2 (2020-03-26) Graph InfoClust (GIC) — 81.7 (2020-09-15) SSGC — 83.0 (2021-01-01) Self-supervised GraphMAE — 84.2 (2022-05-22) TREE-G — 83.5 (2022-07-06) ScaleNet — 82.3 (2024-11-28) SEGCN — 83.5 (2018-09-26) LDS-GNN — 84.1 (2019-03-28) DSGCN — 84.2 (2020-03-26)
RankModel AccuracyMicro F1 PaperCodeYear
1 DSGCN 84.2 Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks balcilar/Spectral-Designed-Graph-Convolutions · sidneyarcidiacono/UnderstandingGCNs 2020
1 Self-supervised GraphMAE 84.2 GraphMAE: Self-Supervised Masked Graph Autoencoders thudm/graphmae · thudm/graphmae2 · wehos/cellt 2022
3 LDS-GNN 84.1 Learning Discrete Structures for Graph Neural Networks lucfra/LDS · lucfra/LDS-GNN 2019
4 SEGCN 83.5 ± 0.4 Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning RoyalVane/SEGCN 2018
5 TREE-G 83.5 TREE-G: Decision Trees Contesting Graph Neural Networks mayabechlerspeicher/tree-g 2022
6 SSGC 83.0 Simple Spectral Graph Convolution allenhaozhu/SSGC · hazdzz/SSGC 2021
7 ScaleNet 82.3±1.1 Scale Invariance of Graph Neural Networks qin87/scalenet 2024
8 Graph InfoClust (GIC) 81.7 ± 1.5 Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning cmavro/Graph-InfoClust-GIC · cmavro/HeMI 2020
9 PairE 75.12 Graph Representation Learning Beyond Node and Homophily syvail/PairE-Graph-Representation-Learning-Beyond-Node-and-Homophily 2022
1–9 / 9 페이지당 10 20 50 100