paper-with-me

Node Classification 벤치마크

Node Classification on Coauthor CS

24개 결과 · ⬇ CSV · JSON

Accuracy

88.7 90.69 92.67 94.66 96.64 2019-09 2026-09 GraphMix (GCN) — 91.83 (2019-09-25) GCN (PPR Diffusion) — 93.01 (2019-10-28) GCN-LPA — 94.8 (2020-02-17) SIGN — 91.98 (2020-04-23) DAGNN (Ours) — 92.8 (2020-07-18) SNoRe — 88.7 (2020-09-08) Graph InfoClust (GIC) — 89.4 (2020-09-15) CoLinkDist — 95.8 (2021-06-16) CoLinkDistMLP — 95.74 (2021-06-16) LinkDistMLP — 95.68 (2021-06-16) LinkDist — 95.66 (2021-06-16) 3ference — 95.99 (2022-04-11) Exphormer — 94.93 (2023-03-10) NCGCN — 96.64 (2023-06-04) NCSAGE — 96.48 (2023-06-04) HH-GraphSAGE — 95.13 (2023-08-17) GraphSAGE — 95.11 (2023-08-17) HH-GCN — 94.71 (2023-08-17) GCN — 94.06 (2023-08-17) GraphSAGE — 96.38 (2024-06-13) GNNMoE(GCN-like P) — 95.81 (2024-12-11) GNNMoE(GAT-like P) — 95.72 (2024-12-11) GNNMoE(SAGE-like P) — 95.68 (2024-12-11) GraphMix (GCN) — 91.83 (2019-09-25) GCN (PPR Diffusion) — 93.01 (2019-10-28) GCN-LPA — 94.8 (2020-02-17) CoLinkDist — 95.8 (2021-06-16) 3ference — 95.99 (2022-04-11) NCGCN — 96.64 (2023-06-04)
RankModel AccuracyInference Time (ms) PaperCodeYear
1 NCGCN 96.64 ± 0.29– Clarify Confused Nodes via Separated Learning GISec-Team/NCGNN 2023
2 NCSAGE 96.48 ± 0.25– Clarify Confused Nodes via Separated Learning GISec-Team/NCGNN 2023
3 GraphSAGE 96.38±0.11– Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification LUOyk1999/tunedGNN 2024
4 3ference 95.99%– Inferring from References with Differences for Semi-Supervised Node Classification on Graphs cf020031308/3ference 2022
5 GNNMoE(GCN-like P) 95.81±0.26– Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
6 CoLinkDist 95.80%– Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages cf020031308/LinkDist · cf020031308/LinkDist 2021
7 CoLinkDistMLP 95.74%– Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages cf020031308/LinkDist · cf020031308/LinkDist 2021
8 GNNMoE(GAT-like P) 95.72±0.23– Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
9 LinkDistMLP 95.68%– Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages cf020031308/LinkDist · cf020031308/LinkDist 2021
10 GNNMoE(SAGE-like P) 95.68±0.24– Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
11 LinkDist 95.66%– Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages cf020031308/LinkDist · cf020031308/LinkDist 2021
12 HH-GraphSAGE 95.13%– Half-Hop: A graph upsampling approach for slowing down message passing nerdslab/halfhop 2023
13 GraphSAGE 95.11%– Half-Hop: A graph upsampling approach for slowing down message passing nerdslab/halfhop 2023
14 Exphormer 94.93±0.46%– Exphormer: Sparse Transformers for Graphs hamed1375/exphormer 2023
15 GCN-LPA 94.8 ± 0.4– Unifying Graph Convolutional Neural Networks and Label Propagation hwwang55/GCN-LPA · achalagarwal/gcn-lpa 2020
16 HH-GCN 94.71%– Half-Hop: A graph upsampling approach for slowing down message passing nerdslab/halfhop 2023
17 GCN 94.06%– Half-Hop: A graph upsampling approach for slowing down message passing nerdslab/halfhop 2023
18 GCN (PPR Diffusion) 93.01%– Diffusion Improves Graph Learning klicperajo/gdc · jhngjng/naq-pytorch · hazdzz/GDC 2019
19 DAGNN (Ours) 92.8%– Towards Deeper Graph Neural Networks dmlc/dgl · mengliu1998/DeeperGNN · divelab/DeeperGNN 2020
20 SIGN 91.98 ± 0.50– SIGN: Scalable Inception Graph Neural Networks dmlc/dgl · twitter-research/sign · facebookresearch/NARS · +2 2020
1–20 / 24 다음 → 페이지당 10 20 50 100