paper-with-me

Node Classification on Non-Homophilic (Heterophilic) Graphs 벤치마크

Node Classification on Non-Homophilic (Heterophilic) Graphs on Texas(60%/20%/20% random splits)

32개 결과 · ⬇ CSV · JSON

1:1 Accuracy

67.57 74.82 82.06 89.31 96.56 2016-09 2026-09 GCN — 83.11 (2016-09-09) GraphSAGE — 79.03 (2017-06-07) GAT — 78.87 (2017-10-30) APPNP — 91.18 (2018-10-14) SGC-1 — 83.28 (2019-02-19) SGC-2 — 81.31 (2019-02-19) MixHop — 76.39 (2019-04-30) Snowball-2 — 83.11 (2019-06-05) Snowball-3 — 83.11 (2019-06-05) Geom-GCN* — 67.57 (2020-02-13) GPRGNN — 92.92 (2020-06-14) MLP-2 — 92.26 (2020-06-14) H2GCN — 85.9 (2020-06-20) GCNII* — 88.52 (2020-07-04) GCNII — 82.46 (2020-07-04) FAGCN — 88.85 (2021-01-04) BernNet — 93.12 (2021-06-21) ACM-GCN++ — 96.56 (2022-10-14) ACM-Snowball-2 — 95.74 (2022-10-14) ACMII-GCN+ — 95.41 (2022-10-14) ACMII-Snowball-2 — 95.25 (2022-10-14) ACMII-GCN — 95.08 (2022-10-14) ACM-GCN+ — 94.92 (2022-10-14) ACM-Snowball-3 — 94.75 (2022-10-14) ACMII-Snowball-3 — 94.75 (2022-10-14) ACMII-GCN++ — 94.75 (2022-10-14) ACM-SGC-1 — 93.61 (2022-10-14) ACM-SGC-2 — 93.44 (2022-10-14) ACM-GCNII* — 93.28 (2022-10-14) ACM-GCNII — 92.46 (2022-10-14) GCN+JK — 80.66 (2022-10-14)  GAT+JK — 75.41 (2022-10-14) GCN — 83.11 (2016-09-09) APPNP — 91.18 (2018-10-14) GPRGNN — 92.92 (2020-06-14) BernNet — 93.12 (2021-06-21) ACM-GCN++ — 96.56 (2022-10-14)
RankModel 1:1 Accuracy PaperCodeYear
1 ACM-GCN++ 96.56 ± 2 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
2 ACM-Snowball-2 95.74 ± 2.22 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
3 ACMII-GCN+ 95.41 ± 2.82 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
4 ACMII-Snowball-2 95.25 ± 1.55 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
5 ACMII-GCN 95.08 ± 2.07 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
6 ACM-GCN+ 94.92 ± 2.79 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
7 ACM-Snowball-3 94.75 ± 2.41 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
8 ACMII-Snowball-3 94.75 ± 3.09 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
9 ACMII-GCN++ 94.75 ± 2.91 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
10 ACM-SGC-1 93.61 ± 1.55 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
11 ACM-SGC-2 93.44 ± 2.54 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
12 ACM-GCNII* 93.28 ± 2.79 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
13 BernNet 93.12 ± 0.65 BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation ivam-he/BernNet 2021
14 GPRGNN 92.92 ± 0.61 Adaptive Universal Generalized PageRank Graph Neural Network jianhao2016/GPRGNN 2020
15 ACM-GCNII 92.46 ± 1.97 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
16 MLP-2 92.26 ± 0.71 Adaptive Universal Generalized PageRank Graph Neural Network jianhao2016/GPRGNN 2020
17 APPNP 91.18 ± 0.70 Predict then Propagate: Graph Neural Networks meet Personalized PageRank dmlc/dgl · dmlc/dgl · benedekrozemberczki/APPNP · +2 2018
18 FAGCN 88.85 ± 4.39 Beyond Low-frequency Information in Graph Convolutional Networks bdy9527/FAGCN 2021
19 GCNII* 88.52 ± 3.02 Simple and Deep Graph Convolutional Networks chennnM/GCNII · chennnM/GCNII · zhanglab-aim/cancer-net · +1 2020
20 H2GCN 85.90 ± 3.53 Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs GemsLab/H2GCN · GitEventhandler/H2GCN-PyTorch · sxwee/GNNsIMPL · +1 2020
1–20 / 32 다음 → 페이지당 10 20 50 100