paper-with-me

Node Classification 벤치마크

Node Classification on Facebook

8개 결과 · ⬇ CSV · JSON

Accuracy

38.9 53.06 67.22 81.37 95.53 2016-09 2026-09 GCN_cheby (Kipf and Welling, 2017) — 64.6 (2016-09-09) GCN (Kipf and Welling, 2017) — 57.5 (2016-09-09) GraphSAGE (Hamilton et al., [2017a]) — 38.9 (2017-06-07) Intersection (Li et al., 2018) — 59.8 (2018-01-22) DEMO-Net(weight) — 91.9 (2019-06-05) GNNMoE(GCN-like P) — 95.53 (2024-12-11) GNNMoE(GAT-like P) — 95.21 (2024-12-11) GNNMoE(SAGE-like P) — 94.63 (2024-12-11) GCN_cheby (Kipf and Welling, 2017) — 64.6 (2016-09-09) DEMO-Net(weight) — 91.9 (2019-06-05) GNNMoE(GCN-like P) — 95.53 (2024-12-11)
RankModel Accuracy PaperCodeYear
1 GNNMoE(GCN-like P) 95.53±0.35 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
2 GNNMoE(GAT-like P) 95.21±0.25 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
3 GNNMoE(SAGE-like P) 94.63±0.36 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
4 DEMO-Net(weight) 91.9 DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification jwu4sml/DEMO-Net 2019
5 GCN_cheby (Kipf and Welling, 2017) 64.6 Semi-Supervised Classification with Graph Convolutional Networks dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 2016
6 Intersection (Li et al., 2018) 59.8 Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning liqimai/gcn 2018
7 GCN (Kipf and Welling, 2017) 57.5 Semi-Supervised Classification with Graph Convolutional Networks dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 2016
8 GraphSAGE (Hamilton et al., [2017a]) 38.9 Inductive Representation Learning on Large Graphs pyg-team/pytorch_geometric · dmlc/dgl · dmlc/dgl · +17 2017
1–8 / 8 페이지당 10 20 50 100