Research map / Learning theory and algorithms / Kernels and regression theory
Dimension Reduction With Prior Information for Knowledge Discovery
Anh Tuan Bui
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 |
|---|---|---|---|
| condition on known feature(s) instead of metric MDS | metric MDS · Facial expressions | average canonical correlation: 0.71 -> 0.94 (known {AR}) | Improved |
| condition on known feature PU only | metric MDS · Facial expressions | average canonical correlation: 0.71 -> 0.85 | Improved |
| use two known features {PU, AR} rather than one (ablation) | conditional MDS · Facial expressions | average canonical correlation: 0.94 -> 0.89 (AR vs PU, AR) | No clear effect |
| condition on texture and rotation with KL dissimilarity | metric MDS · Textile fabrics (KL) | average canonical correlation: 0.66 -> 0.99 | Improved |
| condition on texture and rotation with Euclidean distance | metric MDS · Textile fabrics (ED) | average canonical correlation: 0.24 -> 0.61 | Improved |
| use KL dissimilarity instead of Euclidean distance (ablation) | conditional MDS · Textile fabrics | average canonical correlation: 0.61 -> 0.99 | Improved |
| condition on 4 known car features | metric MDS · Car-brand perception | average canonical correlation: .81 -> .90 | Improved |
| add Eco as fifth known feature (ablation) | conditional MDS · Car-brand perception | average canonical correlation: .90 -> .94 | Improved |
| add Design as sixth known feature (ablation) | conditional MDS · Car-brand perception | average canonical correlation: .94 -> .97 | Improved |
| condition on 4 known features vs ISOMAP | ISOMAP · Car-brand perception | average canonical correlation: .74 -> .90 | Improved |
| add irrelevant known features up to about 30 (ablation) | conditional MDS · Car-brand perception (N=100) | MSE of b estimates: slightly increases up to around 30, then stabilizes | Mixed |
| run UMAP for 10000 iterations instead of 5000 | UMAP · Car-brand perception N=2000 | average canonical correlation: 0.56 -> 0.60 | Improved |
Closest papers by meaning
- Multidimensional Scaling on Multiple Input Distance Matrices (AAAI 2017 · similarity 0.84)
- Multidimensional Scaling: Approximation and Complexity (ICML 2021 · similarity 0.84)
- Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms (NeurIPS 2024 · similarity 0.84)
- On Probabilistic Embeddings in Optimal Dimension Reduction (JMLR 2025 · similarity 0.83)
- Enhancing Sufficient Dimension Reduction via Hellinger Correlation (ICML 2024 · similarity 0.83)
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 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.
