Research map / Graph learning / Graph self-supervised learning
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
Federico Lopez, Beatrice Pozzetti, Steve Trettel, Michael Strube, Anna Wienhard
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 the Siegel space with the F1 Finsler metric instead of Euclidean geometry | Graph reconstruction embeddings · 4D Grid | D_avg: 11.24$\pm$0.00 -> 0.01$\pm$0.00 | Improved |
| Use the Siegel space with the F1 Finsler metric rather than a product of Euclidean and hyperbolic spaces | Graph reconstruction embeddings · Tree × Grid | D_avg: 9.20$\pm$0.01 -> 0.81$\pm$0.08 | Improved |
| Use Siegel S4 F1 rather than Siegel S4 with the Riemannian metric (ablation) | Graph reconstruction embeddings · Tree × Grid | D_avg: 9.13$\pm$0.01 -> 0.81$\pm$0.08 | Improved |
| Use Siegel S4 F1 rather than Siegel S4 F∞ (ablation) | Graph reconstruction embeddings · Grid ◇ Trees | D_avg: 10.48$\pm$0.21 -> 0.84$\pm$0.06 | Improved |
| Use Siegel S4 F1 rather than hyperbolic 20D | Graph reconstruction embeddings · Tree | mAP: 100.00 -> 91.57 | Hurt |
| Use Siegel S4 F1 rather than SPD6 | Graph reconstruction embeddings · bio-diseasome | D_avg: 2.54$\pm$0.00 -> 1.55$\pm$0.04 | Improved |
| Use Siegel S4 F1 rather than Siegel S4 F∞ (ablation) | Graph reconstruction embeddings · EuroRoad | mAP: 72.03 -> 94.63 | Improved |
| Use Siegel S4 F1 rather than Siegel S4 F∞ (ablation) | Recommender systems · lastfm | HR@10: 53.8$\pm$1.7 -> 61.1$\pm$1.2 | Improved |
| Use Siegel S4 F1 rather than Siegel S4 Riemannian (ablation) | Recommender systems · ml-1m | HR@10: 53.8$\pm$0.3 -> 52.9$\pm$0.6 | Hurt |
| Use Siegel S4 F1 rather than SPD6 | Node classification embeddings · Zoo | accuracy: 88.7$\pm$2.2 -> 90.7$\pm$1.5 | Improved |
Closest papers by meaning
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.90)
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 2025 · similarity 0.88)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.87)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.87)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.87)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.87)
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.
