paper-with-me

Node Classification 벤치마크

Node Classification on Actor

62개 결과 · ⬇ CSV · JSON

Accuracy

28.42 32.29 36.16 40.02 43.89 2019-04 2026-11 MixHop — 32.22 (2019-04-30) Geom-GCN-P — 31.63 (2020-02-13) Geom-GCN-S — 30.3 (2020-02-13) Geom-GCN-I — 29.09 (2020-02-13) NLMLP  — 37.9 (2020-05-29) NLGCN  — 31.6 (2020-05-29) NLGAT  — 29.5 (2020-05-29) GPRGCN — 35.16 (2020-06-14) H2GCN-2 — 34.49 (2020-06-20) H2GCN-1 — 34.31 (2020-06-20) GCNII — 37.44 (2020-07-04) FAGCN — 34.82 (2021-01-04) GGCN — 37.54 (2021-02-12) FSGNN (8-hop) — 35.75 (2021-05-17) WRGAT — 36.53 (2021-06-11) HLP Concat — 34.59 (2021-06-24) LINKX — 36.1 (2021-10-27) CNMPGNN — 36.25 (2021-11-15) SDRF — 28.42 (2021-11-29) O(d)-NSD — 37.81 (2022-02-09) Gen-NSD — 37.8 (2022-02-09) Diag-NSD — 37.79 (2022-02-09) GloGNN++ — 37.7 (2022-05-15) GloGNN — 37.35 (2022-05-15) UDGNN (GCN) — 36.13 (2022-05-30) LSC-GNN — 36.2 (2022-06-06) CT-Layer — 31.98 (2022-06-15) CT-Layer (PE) — 29.35 (2022-06-15) GPRGNN+DHGR — 37.43 (2022-09-17) ACM-GCN++ — 37.31 (2022-10-14) ACMII-GCN++ — 37.09 (2022-10-14) ACM-GCN — 36.63 (2022-10-14) ACMII-GCN — 36.31 (2022-10-14) ACM-GCN+ — 36.26 (2022-10-14) ACMII-GCN+ — 36.14 (2022-10-14) ACM-SGC-2 — 36.04 (2022-10-14) ACM-SGC-1 — 35.49 (2022-10-14) Graph ESN — 34.5 (2022-10-27) IIE-GNN — 39.91 (2022-11-20) Ordered GNN — 37.99 (2023-02-03) GCNH — 36.89 (2023-04-21) GESN — 34.56 (2023-05-14) SADE-GCN — 37.91 (2023-05-28) NCSAGE — 43.89 (2023-06-04) NCGCN — 43.16 (2023-06-04) DJ-GNN — 36.93 (2023-06-29) ChebNet+Bregman — 35.92 (2023-09-12) 2-HiGCN — 41.81 (2023-09-22) SignGT — 38.65 (2023-10-17) CATv3-sup — 38.5 (2023-12-14) LHS — 38.87 (2023-12-27) HiGNN — 37.21 (2024-03-26) HDP — 37.26 (2024-05-31) M2M-GNN — 36.72 (2024-05-31) TE-GCNN — 37.5 (2024-06-08) RDGNN-I — 38.69 (2024-06-16) MGNN + Hetero-S (4 layers) — 35.99 (2024-06-18) GGCN + UniGAP — 37.69 (2024-07-28) GNNMoE(SAGE-like P) — 37.97 (2024-12-11) GNNMoE(GAT-like P) — 37.76 (2024-12-11) GNNMoE(GCN-like P) — 37.59 (2024-12-11) MbaGCN — 37.97 (2025-01-26) MixHop — 32.22 (2019-04-30) NLMLP  — 37.9 (2020-05-29) IIE-GNN — 39.91 (2022-11-20) NCSAGE — 43.89 (2023-06-04)
RankModel Accuracy PaperCodeYear
1 NCSAGE 43.89 ± 1.33 Clarify Confused Nodes via Separated Learning GISec-Team/NCGNN 2023
2 NCGCN 43.16 ± 1.32 Clarify Confused Nodes via Separated Learning GISec-Team/NCGNN 2023
3 2-HiGCN 41.81±0.52 Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes yiminghh/higcn 2023
4 IIE-GNN 39.91 ± 2.41 Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach 2022
5 LHS 38.87±1.0 Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks 2023
6 RDGNN-I 38.69 ± 1.41 Graph Neural Reaction Diffusion Models 2024
7 SignGT 38.65±0.32 SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning 2023
8 CATv3-sup 38.5±1.2 CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph geox-lab/cat 2023
9 Ordered GNN 37.99 ± 1.00 Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing lumia-group/orderedgnn 2023
10 MbaGCN 37.97±0.91 Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space 2025
11 GNNMoE(SAGE-like P) 37.97±1.01 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
12 SADE-GCN 37.91 ± 0.97 Self-attention Dual Embedding for Graphs with Heterophily 2023
13 NLMLP  37.9 ± 1.3 Non-Local Graph Neural Networks divelab/Non-Local-GNN 2020
14 O(d)-NSD 37.81 ± 1.15 Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs twitter-research/neural-sheaf-diffusion 2022
15 Gen-NSD 37.80 ± 1.22 Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs twitter-research/neural-sheaf-diffusion 2022
16 Diag-NSD 37.79 ± 1.01 Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs twitter-research/neural-sheaf-diffusion 2022
17 GNNMoE(GAT-like P) 37.76±0.98 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
18 GloGNN++ 37.7 ± 1.40 Finding Global Homophily in Graph Neural Networks When Meeting Heterophily recklessronan/glognn 2022
19 GGCN + UniGAP 37.69 ± 1.2 UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks wangxiaotang0906/unigap 2024
20 GNNMoE(GCN-like P) 37.59±1.36 Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification GISec-Team/GNNMoE 2024
1–20 / 62 다음 → 페이지당 10 20 50 100