Research map / Probabilistic and scientific modeling / Variational and generative sampling
Improving Local Identifiability in Probabilistic Box Embeddings
Shib Dasgupta, Michael Boratko, Dongxu Zhang, Luke Vilnis, Xiang Li, 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 GumbelBox instead of SmoothBox | probabilistic box embeddings · Mammal Hierarchy, 1d | MRR: 0.851 -> 0.934 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · Mammal Hierarchy, 2d | MRR: 0.927 -> 0.981 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · Balanced Tree (small), 1d | MRR: 0.691 -> 0.971 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · Balanced Tree (small), 2d | MRR: 1.000 -> 1.000 | No clear effect |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · Random Tree (large), 1d | MRR: 0.015 -> 0.058 | Improved |
| Use GumbelBox instead of GaussianBox | probabilistic box embeddings · Random Tree (large), 2d | MRR: 0.104 -> 0.270 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · WordNet noun hierarchy, without regularization | F1: 45.4 -> 51.2 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · WordNet noun hierarchy, with regularization | F1: 60.2 -> 62.6 | Improved |
| Use GumbelBox instead of GaussianBox | probabilistic box embeddings · WordNet noun hierarchy | F1: 43.3 -> 51.2; 58.6 -> 62.6 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · MovieLens | KL: 0.0138 -> 0.0120 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · MovieLens | Pearson R: 0.8985 -> 0.9019 | Improved |
| Use GumbelBox instead of SmoothBox | probabilistic box embeddings · MovieLens | Spearman R: 0.8977 -> 0.9020 | Improved |
Closest papers by meaning
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.86)
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.85)
- Union-over-Intersections: Object Detection beyond Winner-Takes-All (ICLR 2025 · similarity 0.84)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.84)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.83)
- Disentangled Representation Learning with the Gromov-Monge Gap (ICLR 2025 · similarity 0.83)
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.
