Research map / Graph learning / Graph algorithms and clustering
Manifold structure in graph embeddings
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 |
|---|---|---|---|
| use random forest instead of least-squares on 100-dim spectral embedding | regression on spectral embedding · Graph regression | out-of-sample MSE: 1.63 -> 1.11 | Improved |
| use neural network instead of least-squares | regression on spectral embedding · Graph regression | out-of-sample MSE: 1.63 -> 1.25 | Improved |
| use Lasso instead of least-squares | regression on spectral embedding · Graph regression | out-of-sample MSE: 1.63 -> 1.58 | Improved |
| nonlinear manifold-exploiting regressors vs linear ones | regression on spectral embedding · Graph regression | out-of-sample MSE: 1.11 vs 1.58 | Improved |
| t-SNE instead of direct spectral embedding into R^2 (linear reduction) | spectral embedding visualisation · Los Alamos / Yelp graphs | visual structure | Improved |
| UMAP instead of t-SNE | spectral embedding visualisation · Los Alamos / Yelp graphs | visual structure | No clear effect |
| choose D-hat by profile-likelihood rank selection (6) instead of 10 | spectral embedding · Los Alamos network flow | embedding dimension: 10 -> 6 | No clear effect |
Closest papers by meaning
- Improving Embedding of Graphs With Missing Data by Soft Manifolds (TPAMI 2025 · similarity 0.90)
- Computationally Tractable Riemannian Manifolds for Graph Embeddings (AAAI 2021 · similarity 0.88)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.86)
- Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data (ICML 2025 · similarity 0.85)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.85)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 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.
