paper-with-me

Node Classification 벤치마크

Node Classification on PubMed (60%/20%/20% random splits)

37개 결과 · ⬇ CSV · JSON

1:1 Accuracy

83.28 85.45 87.62 89.78 91.95 2016-09 2026-09 GCN — 88.9 (2016-09-09) GraphSAGE — 86.85 (2017-06-07) GAT — 83.28 (2017-10-30) APPNP — 85.02 (2018-10-14) SGC-1 — 85.5 (2019-02-19) SGC-2 — 85.36 (2019-02-19) MixHop — 87.04 (2019-04-30) Snowball-2 — 89.04 (2019-06-05) Snowball-3 — 88.8 (2019-06-05) Geom-GCN* — 90.05 (2020-02-13) GPRGNN — 85.07 (2020-06-14) H2GCN — 87.78 (2020-06-20) GCNII* — 89.98 (2020-07-04) GCNII — 89.8 (2020-07-04) FAGCN — 89.98 (2021-01-04) BernNet — 88.48 (2021-06-21) ACM-Snowball-3 — 91.44 (2022-10-14) ACMII-Snowball-3 — 91.31 (2022-10-14) ACMII-GCN+ — 90.96 (2022-10-14) ACM-Snowball-2 — 90.81 (2022-10-14) ACMII-GCN — 90.74 (2022-10-14) ACM-GCN — 90.66 (2022-10-14) ACMII-GCN++ — 90.63 (2022-10-14) ACMII-Snowball-2 — 90.56 (2022-10-14) ACM-GCN+ — 90.46 (2022-10-14) ACM-GCN++ — 90.39 (2022-10-14) ACM-GCNII* — 90.18 (2022-10-14) ACM-GCNII — 90.12 (2022-10-14) GCN+JK — 90.09 (2022-10-14)  GAT+JK — 89.15 (2022-10-14) ACM-SGC-2 — 88.79 (2022-10-14) ACM-SGC-1 — 87.75 (2022-10-14) MLP-2 — 86.43 (2022-10-14) NFGNN — 89.89 (2022-12-07) Graph-MLP + SAF — 90.64 (2023-06-15) NHGCN — 91.56 (2023-10-21) GNNDLD — 91.95 (2024-02-26) GCN — 88.9 (2016-09-09) Snowball-2 — 89.04 (2019-06-05) Geom-GCN* — 90.05 (2020-02-13) ACM-Snowball-3 — 91.44 (2022-10-14) NHGCN — 91.56 (2023-10-21) GNNDLD — 91.95 (2024-02-26)
RankModel 1:1 Accuracy PaperCodeYear
1 GNNDLD 91.95±0.19 GNNDLD: Graph Neural Network with Directional Label Distribution 2024
2 NHGCN 91.56 ± 0.50 Neighborhood Homophily-Guided Graph Convolutional Network rockcor/NHGCN 2023
3 ACM-Snowball-3 91.44 ± 0.59 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
4 ACMII-Snowball-3 91.31 ± 0.6 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
5 ACMII-GCN+ 90.96 ± 0.62 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
6 ACM-Snowball-2 90.81 ± 0.52 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
7 ACMII-GCN 90.74 ± 0.5 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
8 ACM-GCN 90.66 ± 0.47 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
9 Graph-MLP + SAF 90.64 ± 0.46% The Split Matters: Flat Minima Methods for Improving the Performance of GNNs foisunt/fmms-in-gnns 2023
10 ACMII-GCN++ 90.63 ± 0.56 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
11 ACMII-Snowball-2 90.56 ± 0.39 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
12 ACM-GCN+ 90.46 ± 0.69 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
13 ACM-GCN++ 90.39 ± 0.33 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
14 ACM-GCNII* 90.18 ± 0.51 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
15 ACM-GCNII 90.12 ± 0.4 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
16 GCN+JK 90.09 ± 0.68 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
17 Geom-GCN* 90.05 Geom-GCN: Geometric Graph Convolutional Networks bingzhewei/geom-gcn · graphdml-uiuc-jlu/geom-gcn · alexfanjn/geomgcn_pyg · +1 2020
18 FAGCN 89.98 ± 0.54 Beyond Low-frequency Information in Graph Convolutional Networks bdy9527/FAGCN 2021
19 GCNII* 89.98 ± 0.52 Simple and Deep Graph Convolutional Networks chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1 2020
20 NFGNN 89.89±0.68 Node-oriented Spectral Filtering for Graph Neural Networks SsGood/NFGNN 2022
1–20 / 37 다음 → 페이지당 10 20 50 100