Research map / Label-efficient and robust learning / Recognition and long-tail
Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction
Benoît Colange, Jaakko Peltonen, Michael Aupetit, Denys Dutykh, Sylvain Lespinats
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 |
|---|---|---|---|
| add class supervision (eps 0 to 0.5) to NeRV | NeRV · Isolet 5 | 10-NN accuracy (%): 71.0 -> 91.9 | Improved |
| increase supervision level eps (ablation) | ClassNeRV · Globe | 10-NN accuracy | Improved |
| raise tau* toward 1 (ablation) | ClassNeRV · Globe | trustworthiness vs continuity | Mixed |
| use ClassNeRV instead of NCA | ClassNeRV · Isolet 5 | neighborhood structure preservation | Improved |
| use ClassNeRV instead of tSNE | ClassNeRV · Isolet 5 | trustworthiness | Hurt |
| use true labels instead of random labels (ablation) | ClassNeRV · Digits | class preservation | Improved |
Closest papers by meaning
- A Study of the Classification of Low-Dimensional Data with Supervised Manifold Learning (JMLR 2018 · similarity 0.88)
- Dimensionality reduction: theoretical perspective on practical measures (NeurIPS 2019 · similarity 0.87)
- Conveyance: A Versatile Framework for Learning in Structured Class Spaces (NeurIPS 2026 · similarity 0.85)
- Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization (NeurIPS 2024 · similarity 0.85)
- Rank-Transformed Dissimilarity Profiles for High-Dimensional Classification (NeurIPS 2026 · similarity 0.84)
- Navigating the Effect of Parametrization for Dimensionality Reduction (NeurIPS 2024 · similarity 0.84)
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.
