Research map / Point clouds / Shape and surface completion
Matrix factorisation and the interpretation of geodesic distance
Nick Whiteley, Annie Gray, Patrick Rubin-Delanchy
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 |
|---|---|---|---|
| Apply Isomap after spectral embedding instead of using the embedding directly | Spectral embedding · Simulated latent position network model | latent position recovery error | Improved |
| Increase the number of nodes in the dense regime | Spectral embedding followed by Isomap · Simulated latent position network model, dense regime | latent position recovery error | Improved |
| Use the sparse regime rather than the dense regime | Spectral embedding followed by Isomap · Simulated latent position network model | latent position recovery error | Hurt |
| Use spectral embedding with p=20 rather than p=10 before Isomap (ablation) | Spectral embedding followed by Isomap · Global flight network | geographic recovery | No clear effect |
| Use spectral embedding with p=2 rather than p=10 before Isomap (ablation) | Spectral embedding followed by Isomap · Global flight network | geographic recovery | Hurt |
| Use UMAP, t-SNE, or node2vec-based combinations | Matrix factorisation followed by nonlinear dimension reduction · Simulated latent position network model | latent position recovery | Mixed |
| Use longitude rather than latitude as the one-dimensional latent position | Isomap on the temperature correlation matrix · Daily temperature correlations across cities | monotone association with estimated latent position | Hurt |
Closest papers by meaning
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.88)
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 2025 · similarity 0.87)
- GeoMM: On Geodesic Perspective for Multi-modal Learning (CVPR 2025 · similarity 0.86)
- Learning Distances from Data with Normalizing Flows and Score Matching (ICML 2025 · similarity 0.86)
- Metric Space Magnitude for Evaluating the Diversity of Latent Representations (NeurIPS 2024 · similarity 0.86)
- MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product (ICML 2025 · 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.
