paper-with-me

Node Classification 벤치마크

Node Classification on roman-empire

7개 결과 · ⬇ CSV · JSON

Accuracy (% )

85.05 86.92 88.8 90.67 92.55 2023-10 2026-09 FaberNet — 92.24 (2023-10-03) Polynormer — 92.55 (2024-03-02) GCN — 91.27 (2024-06-13) GraphHyperConv — 92.27 (2024-07-16) GNNMoE(GAT-like P) — 87.29 (2024-12-11) GNNMoE(SAGE-like P) — 86.0 (2024-12-11) GNNMoE(GCN-like P) — 85.05 (2024-12-11) FaberNet — 92.24 (2023-10-03) Polynormer — 92.55 (2024-03-02)
RankModel Accuracy (% ) PaperCodeYear
1 Polynormer 92.55±0.37 Polynormer: Polynomial-Expressive Graph Transformer in Linear Time cornell-zhang/Polynormer · cornell-zhang/polynormer 2024
2 GraphHyperConv 92.27±0.57 HyperAggregation: Aggregating over Graph Edges with Hypernetworks foisunt/hyperaggregation 2024
3 FaberNet 92.24±0.43 HoloNets: Spectral Convolutions do extend to Directed Graphs ChristianKoke/HoloNets 2023
4 GCN 91.27±0.20 Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification LUOyk1999/tunedGNN 2024
5 GNNMoE(GAT-like P) 87.29±0.60 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
6 GNNMoE(SAGE-like P) 86.00±0.45 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
7 GNNMoE(GCN-like P) 85.05±0.55 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
1–7 / 7 페이지당 10 20 50 100