Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Embeddings into Entropic Wasserstein Spaces
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 |
|---|---|---|---|
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · RG-65 | Spearman correlation: 0.32 -> 0.81 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · WS-353 | Spearman correlation: 0.15 -> 0.33 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · WS-353-S | Spearman correlation: 0.23 -> 0.44 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · WS-353-R | Spearman correlation: 0.05 -> 0.21 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · MC-30 | Spearman correlation: 0.04 -> 0.54 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · Rare-Word | Spearman correlation: 0.06 -> 0.10 | Mixed |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · MEN | Spearman correlation: 0.25 -> 0.26 | No clear effect |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · MTurk-287 | Spearman correlation: 0.40 -> 0.49 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · MTurk-771 | Spearman correlation: 0.11 -> 0.25 | Helped |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · SimLex-999 | Spearman correlation: 0.09 -> 0.07 | Hurt |
| Increase ground-space dimensionality from 2D to 4D (ablation) | Wasserstein word embeddings · Verb-143 | Spearman correlation: 0.03 -> 0.16 | Helped |
| Use Wasserstein rather than Euclidean or hyperbolic embeddings | Network metric embeddings · Random scale-free, small-world, and community-structured networks | mean distortion | Helped |
Closest papers by meaning
- Fourier Sliced-Wasserstein Embedding for Multisets and Measures (ICLR 2025 · similarity 0.89)
- Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy (ICLR 2025 · similarity 0.88)
- By Tying Embeddings You Are Assuming the Distributional Hypothesis (ICML 2024 · similarity 0.86)
- Structural Entropy Guided Probabilistic Coding (AAAI 2025 · similarity 0.86)
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.85)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 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.