paper-with-me

Node Classification 벤치마크

Node Classification on CiteSeer with Public Split: fixed 20 nodes per class

40개 결과 · ⬇ CSV · JSON

Accuracy

61.5 65.5 69.5 73.5 77.5 2015-09 2026-09 GCN-FP — 61.5 (2015-09-30) DCNN — 69.4 (2015-11-06) GGNN — 64.6 (2015-11-17) ChebyNet — 70.1 (2016-06-30) MPNN — 64.0 (2017-04-04) GraphSAGE — 67.2 (2017-06-07) GAT — 72.5 (2017-10-30) SEGCN — 73.4 (2018-09-26) AdaLanczosNet — 68.7 (2019-01-06) LanczosNet — 66.2 (2019-01-06) H-GCN — 72.8 (2019-02-13) LDS-GNN — 75.0 (2019-03-28) G3NN — 74.5 (2019-05-26) Truncated Krylov — 73.86 (2019-06-05) Snowball (tanh) — 73.32 (2019-06-05) Snowball (linear) — 72.85 (2019-06-05) GraphMix(GCN) — 74.52 (2019-09-25) G-APPNP — 72.0 (2019-10-27) AIR-GCN — 72.9 (2019-11-05) DSGCN — 73.3 (2020-03-26) GRAND — 75.4 (2020-05-22) GCN+GAugO — 73.3 (2020-06-11) GCNII — 73.4 (2020-07-04) DAGNN (Ours) — 73.3 (2020-07-18) SSP — 74.28 (2020-08-21) SSGC — 73.6 (2021-01-01) CPF-tra-APPNP — 74.6 (2021-03-04) CoLinkDistMLP — 70.96 (2021-06-16) CoLinkDist — 70.79 (2021-06-16) LinkDist — 70.27 (2021-06-16) LinkDistMLP — 70.26 (2021-06-16) SuperGAT MX — 72.6 (2022-04-11) GEM — 74.2 (2023-05-31) OKDEEM — 73.53 (2023-05-31) EEM — 72.63 (2023-05-31) Graph-MLP + PGN — 74.73 (2023-06-15) OGC — 77.5 (2023-09-24) GGCM — 74.2 (2023-09-24) GCN — 73.14 (2024-06-13) GCN-FP — 61.5 (2015-09-30) DCNN — 69.4 (2015-11-06) ChebyNet — 70.1 (2016-06-30) GAT — 72.5 (2017-10-30) SEGCN — 73.4 (2018-09-26) LDS-GNN — 75.0 (2019-03-28) GRAND — 75.4 (2020-05-22) OGC — 77.5 (2023-09-24)
RankModel Accuracy PaperCodeYear
1 OGC 77.5 From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited zhengwang100/ogc_ggcm 2023
2 GRAND 75.4 ± 0.4 Graph Random Neural Network for Semi-Supervised Learning on Graphs dmlc/dgl · Grand20/grand · zjunet/dropmessage · +6 2020
3 LDS-GNN 75.0% Learning Discrete Structures for Graph Neural Networks lucfra/LDS · lucfra/LDS-GNN 2019
4 Graph-MLP + PGN 74.73 ± 0.6% The Split Matters: Flat Minima Methods for Improving the Performance of GNNs foisunt/fmms-in-gnns 2023
5 CPF-tra-APPNP 74.6% Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework BUPT-GAMMA/CPF 2021
6 GraphMix(GCN) 74.52 ± 0.59 GraphMix: Improved Training of GNNs for Semi-Supervised Learning vikasverma1077/GraphMix 2019
7 G3NN 74.5% A Flexible Generative Framework for Graph-based Semi-supervised Learning jiaqima/G3NN 2019
8 SSP 74.28 ± 0.67% Optimization of Graph Neural Networks with Natural Gradient Descent russellizadi/ssp 2020
9 GEM 74.2 Graph Entropy Minimization for Semi-supervised Node Classification cf020031308/gem 2023
9 GGCM 74.2 From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited zhengwang100/ogc_ggcm 2023
11 Truncated Krylov 73.86% Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks PwnerHarry/Stronger_GCN 2019
12 SSGC 73.6 Simple Spectral Graph Convolution allenhaozhu/SSGC · hazdzz/SSGC 2021
13 OKDEEM 73.53 Graph Entropy Minimization for Semi-supervised Node Classification cf020031308/gem 2023
14 GCNII 73.4% Simple and Deep Graph Convolutional Networks chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1 2020
15 SEGCN 73.4 ± 0.7 Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning RoyalVane/SEGCN 2018
16 Snowball (tanh) 73.32% Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks PwnerHarry/Stronger_GCN 2019
17 DSGCN 73.3 Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks balcilar/Spectral-Designed-Graph-Convolutions · sidneyarcidiacono/UnderstandingGCNs 2020
18 DAGNN (Ours) 73.3 ± 0.6 Towards Deeper Graph Neural Networks dmlc/dgl · mengliu1998/DeeperGNN · divelab/DeeperGNN 2020
19 GCN+GAugO 73.3 ± 1.1 Data Augmentation for Graph Neural Networks zhao-tong/GAug · andyjzhao/wsdm23-gsr 2020
20 GCN 73.14± 0.67 Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification LUOyk1999/tunedGNN 2024
1–20 / 40 다음 → 페이지당 10 20 50 100