Research map / Learning theory and algorithms / Matrix and tensor methods
Representation Learning of Compositional Data
Marta Avalos, Richard Nock, Cheng Soon Ong, Julien Rouar, Ke Sun
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 CoDA-PCA loss instead of clr-PCA | PCA on compositional data · Atlas and diet swap test sets | JSD and TV test error | Improved |
| use CoDA-PCA loss instead of clr-PCA | PCA on compositional data · Atlas and diet swap test sets | L2-clr test error | Hurt |
| use CoDA-AE loss instead of clr-AE | autoencoder on compositional data · Atlas and diet swap test sets | JSD and TV test error | Improved |
| use CoDA-AE instead of clr-AE | autoencoder · Atlas and diet swap test sets | overfitting robustness | Improved |
| use surrogate S-CoDA-PCA instead of CoDA-PCA | CoDA-PCA · Atlas and diet swap test sets | JSD and TV test error | No clear effect |
| use surrogate S-CoDA-PCA instead of CoDA-PCA | CoDA-PCA · Atlas and diet swap test sets | L2-clr test error | Improved |
Closest papers by meaning
- Does Data Scaling Lead to Visual Compositional Generalization? (ICML 2025 · similarity 0.84)
- Principle Component Trees and Their Persistent Homology (AAAI 2024 · similarity 0.83)
- The tree autoencoder model, with application to hierarchical data visualization (NeurIPS 2024 · similarity 0.83)
- When does compositional structure yield compositional generalization? A kernel theory. (ICLR 2025 · similarity 0.83)
- Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing (NeurIPS 2026 · similarity 0.82)
- In-Context Compositional Learning vis Sparse Coding Transformer (NeurIPS 2025 · similarity 0.82)
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.
