Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Manifold Alignment with Joint Multidimensional Scaling
Dexiong Chen, Bowen Fan, Carlos Oliver, Karsten Borgwardt
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 |
|---|---|---|---|
| Increase embedding dimension from d=2 to d=16 (ablation) | Joint MDS · Bifurcation, Swiss roll, Circular frustum, SNAREseq, scGEM | FOSCTTM: 11.15 -> 7.56; 0.96 -> 0.58; 0.90 -> 0.87; 17.18 -> 15.59; 20.42 -> 18.54 | Improved |
| Increase embedding dimension from d=2 to d=16 (ablation) | Joint MDS · Bifurcation | classification accuracy: 96.0 -> 96.7 | Improved |
| Increase embedding dimension from d=2 to d=16 (ablation) | Joint MDS · Swiss roll | classification accuracy: 99.3 -> 99.3 | No clear effect |
| Increase embedding dimension from d=2 to d=16 (ablation) | Joint MDS · Circular frustum, SNAREseq, scGEM, MNIST-USPS | classification accuracy: 94.0 -> 94.7; 85.5 -> 94.7; 64.4 -> 72.9; 15.0 -> 60.2 | Improved |
| Use Joint MDS with d=16 rather than the strongest listed baseline | Joint MDS · Bifurcation, Swiss roll, scGEM, MNIST-USPS | classification accuracy: 96.7 vs 95.7; 99.3 vs 99.3; 72.9 vs 62.7; 60.2 vs 43.1 | Improved |
| Use Joint MDS with d=16 rather than the strongest listed baseline | Joint MDS · Circular frustum, SNAREseq | classification accuracy: 94.7 vs 95.7; 94.7 vs 98.2 | Hurt |
| Use Joint MDS instead of the strongest listed baseline | Joint MDS · PPI 5%, MIMIC-III top 3 | node correctness / accuracy: 84.31 -> 86.44$\pm$0.33; 27.98 -> 30.24$\pm$1.66 | Improved |
| Use Joint MDS instead of the strongest listed baseline | Joint MDS · PPI 15%, PPI 25%, MIMIC-III top 5 | node correctness / accuracy: 72.31$\pm$0.62 vs 74.35; 55.3$\pm$0.78 vs 67.42; 46.28$\pm$1.51 vs 47.86 | Hurt |
Closest papers by meaning
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 2025 · similarity 0.87)
- Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms (NeurIPS 2024 · similarity 0.86)
- Recovering Manifold Structure Using Ollivier Ricci Curvature (ICLR 2025 · similarity 0.85)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.85)
- ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching (NeurIPS 2026 · similarity 0.84)
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization (ICML 2025 · 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.
