Research map / Graph learning / Graph self-supervised learning
Representation Learning on Spatial Networks
Zheng Zhang, Liang Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Kirchhoff-normalized random spanning tree sampling (ablation) | SGMP · Synthetic spatial diameter | RMSE: 0.748 -> 0.291 | Improved |
| add Kirchhoff-normalized random spanning tree sampling (ablation) | SGMP · Synthetic interaction radius | RMSE: 1.332 -> 1.266 | Improved |
| add Kirchhoff-normalized random spanning tree sampling (ablation) | SGMP · Synthetic clustering coefficient | RMSE: 0.068 -> 0.088 | Hurt |
| add spanning tree sampling (ablation) | SGMP · ESOL | RMSE: 0.646 -> 0.612 | Improved |
| add spanning tree sampling (ablation) | SGMP · HCP brain network | MAE: 0.524 -> 0.555 | Hurt |
| add spanning tree sampling (ablation) | SGMP · BACE | accuracy: 0.830 -> 0.811 | Hurt |
| add spanning tree sampling (ablation) | SGMP · HCP brain network ADR 20% | training time per epoch: 80.96s -> 0.213s | Improved |
| add spanning tree sampling (ablation) | SGMP · HCP brain network ADR 50% | memory feasibility: out-of-memory -> 0.193s | Improved |
| use SGMP (with st) instead of best baseline GatedGNN | synthetic targets · Synthetic dataset | RMSE: 35.7% lower on average | Improved |
Closest papers by meaning
- pathGCN: Learning General Graph Spatial Operators from Paths (ICML 2022 · similarity 0.87)
- Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysis (TPAMI 2023 · similarity 0.87)
- Spatio-Spectral Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
- Designing Specialized Two-Dimensional Graph Spectral Filters for Spatial-Temporal Graph Modeling (AAAI 2025 · similarity 0.86)
- Subgraph Invariant Learning Towards Large-Scale Graph Node Classification (AAAI 2025 · similarity 0.85)
- Road Network Representation Learning with the Third Law of Geography (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
