mlsanityData to 7 Oct 2026

Parametric UMAP embeddings for representation and semi-supervised learning

arXiv 2009.12981 ↗First posted 27 Sep 2020cs.LG cs.CG q-bio.QMcited by 103

Not on the map. Why?

Abstract (arXiv)

UMAP is a non-parametric graph-based dimensionality reduction algorithm using applied Riemannian geometry and algebraic topology to find low-dimensional embeddings of structured data. The UMAP algorithm consists of two steps: (1) Compute a graphical representation of a dataset (fuzzy simplicial complex), and (2) Through stochastic gradient descent, optimize a low-dimensional embedding of the graph. Here, we extend the second step of UMAP to a parametric optimization over neural network weights, learning a parametric relationship between data and embedding. We first demonstrate that Parametric UMAP performs comparably to its non-parametric counterpart while conferring the benefit of a learned parametric mapping (e.g. fast online embeddings for new data). We then explore UMAP as a regularization, constraining the latent distribution of autoencoders, parametrically varying global structure preservation, and improving classifier accuracy for semi-supervised learning by capturing structure in unlabeled data. Google Colab walkthrough: https://colab.research.google.com/drive/1WkXVZ5pnMrm17m0YgmtoNjM_XHdnE5Vp?usp=sharing

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 14; 2023: 14; 2024: 21; 2025: 32; 2026: 16.

103 papers.

Sort:

By area:

  1. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 553
  2. 2021MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extractioncited by 82
  3. 2023V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Modelscited by 65
  4. 2023Reverse Engineering Self-Supervised Learningcited by 33
  5. 2023Learning Topology-Preserving Data Representationscited by 30
  6. 2022From t-SNE to UMAP with contrastive learningcited by 28
  7. 2023Geometric Autoencoders -- What You See is What You Decodecited by 23
  8. 2024WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wildcited by 20
  9. 2022DLME: Deep Local-flatness Manifold Embeddingcited by 16
  10. 2022Unsupervised visualization of image datasets using contrastive learningcited by 16
  11. 2022Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reductioncited by 14
  12. 2024Bridging Vision and Language Spaces with Assignment Predictioncited by 11
38 more
  1. 2022EVNet: An Explainable Deep Network for Dimension Reductioncited by 8
  2. 2022Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Datasetcited by 7
  3. 2023DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentationcited by 7
  4. 2021GenURL: A General Framework for Unsupervised Representation Learningcited by 6
  5. 2025Stop Misusing t-SNE and UMAP for Visual Analyticscited by 6
  6. 2022UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projectioncited by 5
  7. 2022How people talk about each other: Modeling Generalized Intergroup Bias and Emotioncited by 5
  8. 2023ActUp: Analyzing and Consolidating tSNE and UMAPcited by 5
  9. 2024A General Approach for Determining Applicability Domain of Machine Learning Modelscited by 5
  10. 2025The Shape of Attraction in UMAP: Exploring the Embedding Forces in Dimensionality Reductioncited by 5
  11. 2022Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINOcited by 4
  12. 2022ParaDime: A Framework for Parametric Dimensionality Reductioncited by 4
  13. 2023Field-level simulation-based inference with galaxy catalogs: the impact of systematic effectscited by 4
  14. 2024Image-guided topic modeling for interpretable privacy classificationcited by 4
  15. 2025Random Forest Autoencoders for Guided Representation Learningcited by 4
  16. 2025Evaluating Autoencoders for Parametric and Invertible Multidimensional Projectionscited by 4
  17. 2021Dimension Reduction with Prior Information for Knowledge Discoverycited by 3
  18. 2023Augment on Manifold: Mixup Regularization with UMAPcited by 3
  19. 2024Sampling-enabled scalable manifold learning unveils the discriminative cluster structure of high-dimensional datacited by 3
  20. 2024An embedding-based distance for temporal graphscited by 3
  21. 2024Inductive Global and Local Manifold Approximation and Projectioncited by 3
  22. 2024MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualizationcited by 3
  23. 2024Navigating the Effect of Parametrization for Dimensionality Reductioncited by 3
  24. 2021Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learningcited by 2
  25. 2024Adversarial Attacks on Machine Learning-Aided Visualizationscited by 2
  26. 2024Online Posterior Sampling with a Diffusion Priorcited by 2
  27. 2025Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practicescited by 2
  28. 2025Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasetscited by 2
  29. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2
  30. 2021Focusing on Potential Named Entities During Active Label Acquisitioncited by 1
  31. 2022Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphscited by 1
  32. 2023Domain Adaptation via Rebalanced Sub-domain Alignmentcited by 1
  33. 2023Topological Data Analysis in smart manufacturing: State of the art and futuredirectionscited by 1
  34. 2024Exploring the Influence of Dimensionality Reduction on Anomaly Detection Performance in Multivariate Time Seriescited by 1
  35. 2024HistoKernel: Whole Slide Image Level Maximum Mean Discrepancy Kernels for Pan-Cancer Predictive Modellingcited by 1
  36. 2024A Hybrid Framework for Spatial Interpolation: Merging Data-driven with Domain Knowledgecited by 1
  37. 2024Explainable Moral Values: a neuro-symbolic approach to value classificationcited by 1
  38. 2024Federated t-SNE and UMAP for Distributed Data Visualizationcited by 1

50 most cited of 103 All 103 (JSON)