Research map / Graph learning / Graph algorithms and clustering
Learning to Learn Graph Topologies
Xingyue Pu, Tianyue Cao, Xiaoyun Zhang, Xiaowen Dong, Siheng Chen
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 TopoDiffVAE to layer-wise unrolling (ablation) | Unrolling / L2G · Scale-free (BA) | GMSE: 0.1079 $\pm$ .0047 -> 0.0594 $\pm$ .0044 | Improved |
| add TopoDiffVAE to layer-wise unrolling (ablation) | Unrolling / L2G · Random sparse (ER) | GMSE: 0.0898 $\pm$ .0067 -> 0.0746 $\pm$ .0042 | Improved |
| add TopoDiffVAE to layer-wise unrolling (ablation) | Unrolling / L2G · Community (SBM) | GMSE: 0.1199 $\pm$ .0064 -> 0.0735 $\pm$ .0051 | Improved |
| add TopoDiffVAE to layer-wise unrolling (ablation) | Unrolling / L2G · Small-world (WS) | GMSE: 0.1028 $\pm$ .0073 -> 0.0513 $\pm$ .0060 | Improved |
| use independent trainable parameters in each layer instead of shared parameters (ablation) | Unrolling · Scale-free (BA) | GMSE: 0.3018 $\pm$ .0080 -> 0.1079 $\pm$ .0047 | Improved |
| use independent trainable parameters in each layer instead of shared parameters (ablation) | Unrolling · Random sparse (ER) | GMSE: 0.2885 $\pm$ .0075 -> 0.0898 $\pm$ .0067 | Improved |
| use independent trainable parameters in each layer instead of shared parameters (ablation) | Unrolling · Community (SBM) | GMSE: 0.2658 $\pm$ .0108 -> 0.1199 $\pm$ .0064 | Improved |
| use independent trainable parameters in each layer instead of shared parameters (ablation) | Unrolling · Small-world (WS) | GMSE: 0.2007 $\pm$ .0081 -> 0.1028 $\pm$ .0073 | Improved |
| replace the PDS structural proximal projection with learned topological refinement | L2G vs PDS · Scale-free (BA) | GMSE: 0.4033 $\pm$ .0072 -> 0.0594 $\pm$ .0044 | Improved |
| replace the PDS structural proximal projection with learned topological refinement | L2G vs PDS · Random sparse (ER) | GMSE: 0.3799 $\pm$ .0085 -> 0.0746 $\pm$ .0042 | Improved |
| replace the PDS structural proximal projection with learned topological refinement | L2G vs PDS · Community (SBM) | GMSE: 0.3111 $\pm$ .0147 -> 0.0735 $\pm$ .0051 | Improved |
| replace the PDS structural proximal projection with learned topological refinement | L2G vs PDS · Small-world (WS) | GMSE: 0.2180 $\pm$ .0117 -> 0.0513 $\pm$ .0060 | Improved |
Closest papers by meaning
- Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity (ICLR 2025 · similarity 0.89)
- TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration (ICML 2025 · similarity 0.89)
- Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes (AAAI 2024 · similarity 0.88)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · similarity 0.88)
- Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness (ICML 2024 · similarity 0.88)
- TopER: Topological Embeddings in Graph Representation Learning (NeurIPS 2025 · similarity 0.88)
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.
