Research map / Graph learning / Graph self-supervised learning
Computationally Tractable Riemannian Manifolds for Graph Embeddings
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SPD or hyperbolic embeddings instead of Euclidean embeddings | Graph embeddings · Real graph datasets | graph reconstruction | Helped |
| Use SPD-Stein embeddings instead of Euclidean embeddings | Graph embeddings · Real graph datasets | average distortion | Helped |
| Use SPD-Stein embeddings instead of hyperbolic embeddings | Graph embeddings · Facebook graph | F1@1 | Helped |
| Use SPD-Stein embeddings instead of other evaluated spaces | Graph embeddings · Real graph datasets | ranking metrics | Mixed |
| Use a hyperbolic component rather than only non-negatively curved embeddings | Synthetic tree graph embeddings · Full balanced tree and cycle of trees | F1@k | Helped |
| Use Grassmann embeddings instead of spherical embeddings | Compact graph embeddings · cat-cortex dissimilarity dataset | average distortion | Helped |
| Use Grassmann embeddings instead of spherical embeddings | Compact graph embeddings · road-minnesota graph | average distortion | No clear effect |
| Increase RSNE temperature to emphasize global structure | RSNE graph embeddings · Synthetic graphs | F1@k | Mixed |
Closest papers by meaning
- Pseudo-Riemannian Graph Transformer (NeurIPS 2025 · similarity 0.93)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.91)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.90)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.90)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.88)
- Spectro-Riemannian Graph Neural Networks (ICLR 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.