paper-with-me

Node Classification 벤치마크

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

33개 결과 · ⬇ CSV · JSON

1:1 Accuracy

65.65 72.48 79.32 86.16 92.99 2016-09 2026-09 GCN — 87.78 (2016-09-09) GraphSAGE — 86.58 (2017-06-07) GAT — 76.7 (2017-10-30) GCN+JK — 86.9 (2018-02-20) APPNP — 79.41 (2018-10-14) SGC-2 — 85.48 (2019-02-19) SGC-1 — 85.12 (2019-02-19) MixHop — 65.65 (2019-04-30) Snowball-3 — 89.33 (2019-06-05) Snowball-2 — 88.64 (2019-06-05) Geom-GCN* — 85.27 (2020-02-13) GPRGNN — 79.51 (2020-06-14) H2GCN — 87.52 (2020-06-20) GCNII — 88.98 (2020-07-04) GCNII* — 88.93 (2020-07-04) FAGCN — 88.85 (2021-01-04) BernNet — 88.52 (2021-06-21) ACM-GCN+ — 89.75 (2022-10-14) ACM-Snowball-3 — 89.59 (2022-10-14) GAT+JK — 89.52 (2022-10-14) ACMII-GCN++ — 89.47 (2022-10-14) ACMII-Snowball-3 — 89.36 (2022-10-14) ACM-GCN++ — 89.33 (2022-10-14) ACMII-GCN+ — 89.18 (2022-10-14) ACM-GCNII — 89.1 (2022-10-14) ACM-GCNII* — 89.0 (2022-10-14) ACMII-GCN — 89.0 (2022-10-14) ACMII-Snowball-2 — 88.95 (2022-10-14) ACM-Snowball-2 — 88.83 (2022-10-14) ACM-SGC-2 — 87.64 (2022-10-14) ACM-SGC-1 — 86.63 (2022-10-14) MLP-2 — 76.44 (2022-10-14) GNNDLD — 92.99 (2024-02-26) GCN — 87.78 (2016-09-09) Snowball-3 — 89.33 (2019-06-05) ACM-GCN+ — 89.75 (2022-10-14) GNNDLD — 92.99 (2024-02-26)
RankModel 1:1 Accuracy PaperCodeYear
1 GNNDLD 92.99 ±0.9 GNNDLD: Graph Neural Network with Directional Label Distribution 2024
2 ACM-GCN+ 89.75 ± 1.16 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
3 ACM-Snowball-3 89.59 ± 1.58 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
4 GAT+JK 89.52 ± 0.43 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
5 ACMII-GCN++ 89.47 ± 1.08 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
6 ACMII-Snowball-3 89.36 ± 1.26 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
7 Snowball-3 89.33 ± 1.3 Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks PwnerHarry/Stronger_GCN 2019
8 ACM-GCN++ 89.33 ± 0.81 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
9 ACMII-GCN+ 89.18 ± 1.11 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
10 ACM-GCNII 89.1 ± 1.61 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
11 ACM-GCNII* 89.00 ± 1.35 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
12 ACMII-GCN 89.00 ± 0.72 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
13 GCNII 88.98 ± 1.33 Simple and Deep Graph Convolutional Networks chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1 2020
14 ACMII-Snowball-2 88.95 ± 1.04 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
15 GCNII* 88.93 ± 1.37 Simple and Deep Graph Convolutional Networks chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1 2020
16 FAGCN 88.85 ± 1.36 Beyond Low-frequency Information in Graph Convolutional Networks bdy9527/FAGCN 2021
17 ACM-Snowball-2 88.83 ± 1.49 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
18 Snowball-2 88.64 ± 1.15 Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks PwnerHarry/Stronger_GCN 2019
19 BernNet 88.52 ± 0.95 BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation ivam-he/BernNet 2021
20 GCN 87.78 ± 0.96 Semi-Supervised Classification with Graph Convolutional Networks dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 2016
1–20 / 33 다음 → 페이지당 10 20 50 100