Research map / Graph learning / Graph self-supervised learning
Capacity and Bias of Learned Geometric Embeddings for Directed Graphs
Michael Boratko, Dongxu Zhang, Nicholas Monath, Luke Vilnis, Kenneth L. Clarkson, Andrew McCallum
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 BOX embeddings instead of vector models at the lowest dimensions | BOX · Synthetic and real-world directed graphs, 8 params per node | F1 | Improved |
| Use hyperbolic embeddings on tree-based graphs | Hyperbolic · nCRP and balanced trees | F1 | Improved |
| Use hyperbolic embeddings on transitively closed graphs | Hyperbolic · Transitively closed graphs | F1 | Hurt |
| Use vector-based models in low dimensions | SIM, COMPLEX, BILINEAR · Low-dimension graphs | F1 | Hurt |
| Learn temperatures in box model (T-BOX) at higher dimensions (ablation) | BOX · Synthetic and real-world graphs, 32 and 128 params per node | F1 | Improved |
| Learn temperatures in box model with only 8 parameters per node (ablation) | BOX · 8 params per node | F1 | Hurt |
| Learn per-node and per-dimension temperature at fixed dimension (ablation) | BOX · Varied dimensionality | F1 | Improved |
Closest papers by meaning
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.90)
- Modeling Transitivity and Cyclicity in Directed Graphs via Binary Code Box Embeddings (NeurIPS 2022 · similarity 0.89)
- Smoothing the Geometry of Probabilistic Box Embeddings (ICLR 2019 · similarity 0.88)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.88)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.88)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.86)
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.
