paper-with-me

Node Classification 벤치마크

Node Classification on Texas

62개 결과 · ⬇ CSV · JSON

Accuracy

57.36 66.67 75.97 85.28 94.59 2019-04 2026-09 MixHop — 77.84 (2019-04-30) Geom-GCN-P — 67.57 (2020-02-13) Geom-GCN-S — 59.73 (2020-02-13) Geom-GCN-I — 57.58 (2020-02-13) NLMLP  — 85.4 (2020-05-29) NLGCN  — 65.5 (2020-05-29) NLGAT  — 62.6 (2020-05-29) GPRGCN — 81.35 (2020-06-14) H2GCN-1 — 83.24 (2020-06-20) H2GCN-2 — 80.0 (2020-06-20) GCNII — 77.57 (2020-07-04) FAGCN — 76.49 (2021-01-04) GGCN — 84.86 (2021-02-12) FSGNN — 87.3 (2021-05-17) WRGAT — 83.62 (2021-06-11) HLP Concat — 87.57 (2021-06-24) TDGNN-w — 83.0 (2021-08-25) FDGATII — 80.5405 (2021-10-21) LINKX — 74.6 (2021-10-27) CNMPGNN — 85.68 (2021-11-15) SDRF — 64.46 (2021-11-29) O(d)-NSD — 85.95 (2022-02-09) Diag-NSD — 85.67 (2022-02-09) Gen-NSD — 82.97 (2022-02-09) GloGNN — 84.32 (2022-05-15) GloGNN++ — 84.05 (2022-05-15) UDGNN (GCN) — 84.6 (2022-05-30) Conn-NSD — 86.16 (2022-06-17) H2GCN+DHGR — 84.86 (2022-09-17) ACM-GCN+ — 88.38 (2022-10-14) ACM-GCN++ — 88.38 (2022-10-14) ACMII-GCN++ — 88.38 (2022-10-14) ACMII-GCN+ — 88.11 (2022-10-14) ACM-GCN — 87.84 (2022-10-14) ACMII-GCN — 86.76 (2022-10-14) ACM-SGC-1 — 81.89 (2022-10-14) ACM-SGC-2 — 81.89 (2022-10-14) Graph ESN — 84.3 (2022-10-27) IIE-GNN — 85.84 (2022-11-20) Ordered GNN — 86.22 (2023-02-03) GCNH — 87.84 (2023-04-21) SADE-GCN — 86.49 (2023-05-28) DJ-GNN — 92.43 (2023-06-29) UniG-Encoder — 85.4 (2023-08-03) UGT — 86.67 (2023-08-18) ChebNet+Bregman — 84.05 (2023-09-12) 2-HiGCN — 92.45 (2023-09-22) ADPA — 83.8 (2023-12-07) CATv3-sup — 83.0 (2023-12-14) H2GCN-RARE (λ=1.0) — 86.76 (2023-12-15) LHS — 86.32 (2023-12-27) HiGNN — 86.22 (2024-03-26) GRADE-GAT — 88.3 (2024-03-29) M2M-GNN — 89.19 (2024-05-31) TE-GCNN — 84.86 (2024-06-08) RDGNN-S — 94.59 (2024-06-16) RDGNN-I — 93.51 (2024-06-16) MGNN + Hetero-S (8 layers) — 93.09 (2024-06-18) GraphSAGE + UniGAP — 86.52 (2024-07-28) CoED — 84.59 (2024-10-18) LINKX+CausalMP — 57.36 (2024-11-21) DeltaGNN constant — 74.05 (2025-01-10) MixHop — 77.84 (2019-04-30) NLMLP  — 85.4 (2020-05-29) FSGNN — 87.3 (2021-05-17) HLP Concat — 87.57 (2021-06-24) ACM-GCN+ — 88.38 (2022-10-14) DJ-GNN — 92.43 (2023-06-29) 2-HiGCN — 92.45 (2023-09-22) RDGNN-S — 94.59 (2024-06-16)
RankModel Accuracy PaperCodeYear
1 RDGNN-S 94.59 ± 5.97 Graph Neural Reaction Diffusion Models 2024
2 RDGNN-I 93.51 ± 5.93 Graph Neural Reaction Diffusion Models 2024
3 MGNN + Hetero-S (8 layers) 93.09 The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs bingreeky/heterosnoh 2024
4 2-HiGCN 92.45±0.73 Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes yiminghh/higcn 2023
5 DJ-GNN 92.43±3.15 Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters AhmedBegggaUA/TFM 2023
6 M2M-GNN 89.19 ± 4.5 Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs Jinx-byebye/m2mgnn 2024
7 ACM-GCN+ 88.38 ± 3.64 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
8 ACM-GCN++ 88.38 ± 3.43 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
9 ACMII-GCN++ 88.38 ± 3.43 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
10 GRADE-GAT 88.3±3.5 Graph Neural Aggregation-diffusion with Metastability 2024
11 ACMII-GCN+ 88.11 ± 3.24 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
12 ACM-GCN 87.84 ± 4.4 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
13 GCNH 87.84±3.87 GCNH: A Simple Method For Representation Learning On Heterophilous Graphs smartdata-polito/gcnh 2023
14 HLP Concat 87.57 ± 5.44 Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs 2021
15 FSGNN 87.30 ± 5.55 Improving Graph Neural Networks with Simple Architecture Design sunilkmaurya/FSGNN 2021
16 ACMII-GCN 86.76 ± 4.75 Revisiting Heterophily For Graph Neural Networks SitaoLuan/ACM-GNN 2022
17 H2GCN-RARE (λ=1.0) 86.76±5.80 GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy 2023
18 UGT 86.67 ±8.31 Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity nslab-cuk/unified-graph-transformer · nslab-cuk/community-aware-graph-transformer · nslab-cuk/literalkg 2023
19 GraphSAGE + UniGAP 86.52 ± 4.8 UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks wangxiaotang0906/unigap 2024
20 SADE-GCN 86.49±5.12 Self-attention Dual Embedding for Graphs with Heterophily 2023
1–20 / 62 다음 → 페이지당 10 20 50 100