mlsanityData to 7 Oct 2026

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis

arXiv 2601.20173 ↗First posted 28 Jan 2026cs.LG cs.HCcited by 1

Not on the map. Why?

Abstract (arXiv)

We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervised learning approach to more efficiently encode low-dimensional manifold geometry. Central to this approach are maximum manifold capacity representations (MMCRs), which help untangle complex manifolds by compressing variances among locally similar data points while amplifying variance among dissimilar data points. This design is particularly effective for high-dimensional data with substantial intra-cluster variance and curved manifold structures, such as biological or image data. Our qualitative and quantitative evaluations demonstrate that MAPLE can produce clearer visual cluster separations and finer subcluster resolution than UMAP while maintaining tractable computational cost.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 99 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

34 of 99 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  8. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  9. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  10. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  11. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 170
  12. 2020Deep Nearest Neighbor Anomaly Detectioncited by 103
22 more
  1. 2020Parametric UMAP embeddings for representation and semi-supervised learningcited by 103
  2. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  3. 2016Visualizing Large-scale and High-dimensional Datacited by 79
  4. 2017Classification and Geometry of General Perceptual Manifoldscited by 62
  5. 2020Learning Physical Graph Representations from Visual Scenescited by 50
  6. 2020Attraction-Repulsion Spectrum in Neighbor Embeddingscited by 41
  7. 2021On UMAP's true loss functioncited by 32
  8. 2023Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representationscited by 31
  9. 2022Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embeddingcited by 28
  10. 2022From t-SNE to UMAP with contrastive learningcited by 28
  11. 2022Unsupervised visualization of image datasets using contrastive learningcited by 16
  12. 2025Unveiling High-dimensional Backstage: A Survey for Reliable Visual Analytics with Dimensionality Reductioncited by 16
  13. 2023ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddingscited by 15
  14. 2023The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learningcited by 13
  15. 2021Interactive Dimensionality Reduction for Comparative Analysiscited by 12
  16. 2023Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reductioncited by 11
  17. 2021TLDR: Twin Learning for Dimensionality Reductioncited by 9
  18. 2024Dimension Reduction with Locally Adjusted Graphscited by 9
  19. 2024Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representationscited by 8
  20. 2015Connections Between Nuclear Norm and Frobenius Norm Based Representationscited by 7
  21. 2025The Shape of Attraction in UMAP: Exploring the Embedding Forces in Dimensionality Reductioncited by 5
  22. 2024A Large-Scale Sensitivity Analysis on Latent Embeddings and Dimensionality Reductions for Text Spatializationscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A Spectral Decomposition Framework for Multiscale Nonlinear Dimensionality Reductioncited by 0