UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. McInnes, L., Healy, J., & Melville, J. September, 2020. 10334 citations (Semantic Scholar/arXiv) [2025-11-01] arXiv:1802.03426 [stat]

Paper doi abstract bibtex

UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.

@misc{mcinnes_umap_2020,
	title = {{UMAP}: {Uniform} {Manifold} {Approximation} and {Projection} for {Dimension} {Reduction}},
	shorttitle = {{UMAP}},
	url = {http://arxiv.org/abs/1802.03426},
	doi = {10.48550/arXiv.1802.03426},
	abstract = {UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.},
	urldate = {2025-11-01},
	publisher = {arXiv},
	author = {McInnes, Leland and Healy, John and Melville, James},
	month = sep,
	year = {2020},
	note = {10334 citations (Semantic Scholar/arXiv) [2025-11-01]
arXiv:1802.03426 [stat]},
}

Downloads: 0

{"_id":"mnx5m88erK3NJuAca","bibbaseid":"mcinnes-healy-melville-umapuniformmanifoldapproximationandprojectionfordimensionreduction-2020","author_short":["McInnes, L.","Healy, J.","Melville, J."],"bibdata":{"bibtype":"misc","type":"misc","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","shorttitle":"UMAP","url":"http://arxiv.org/abs/1802.03426","doi":"10.48550/arXiv.1802.03426","abstract":"UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.","urldate":"2025-11-01","publisher":"arXiv","author":[{"propositions":[],"lastnames":["McInnes"],"firstnames":["Leland"],"suffixes":[]},{"propositions":[],"lastnames":["Healy"],"firstnames":["John"],"suffixes":[]},{"propositions":[],"lastnames":["Melville"],"firstnames":["James"],"suffixes":[]}],"month":"September","year":"2020","note":"10334 citations (Semantic Scholar/arXiv) [2025-11-01] arXiv:1802.03426 [stat]","bibtex":"@misc{mcinnes_umap_2020,\n\ttitle = {{UMAP}: {Uniform} {Manifold} {Approximation} and {Projection} for {Dimension} {Reduction}},\n\tshorttitle = {{UMAP}},\n\turl = {http://arxiv.org/abs/1802.03426},\n\tdoi = {10.48550/arXiv.1802.03426},\n\tabstract = {UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.},\n\turldate = {2025-11-01},\n\tpublisher = {arXiv},\n\tauthor = {McInnes, Leland and Healy, John and Melville, James},\n\tmonth = sep,\n\tyear = {2020},\n\tnote = {10334 citations (Semantic Scholar/arXiv) [2025-11-01]\narXiv:1802.03426 [stat]},\n}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["McInnes, L.","Healy, J.","Melville, J."],"key":"mcinnes_umap_2020","id":"mcinnes_umap_2020","bibbaseid":"mcinnes-healy-melville-umapuniformmanifoldapproximationandprojectionfordimensionreduction-2020","role":"author","urls":{"Paper":"http://arxiv.org/abs/1802.03426"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"misc","biburl":"https://bibbase.org/zotero/hegera","dataSources":["iwKepCrWBps7ojhDx","nXLpMJvoa6dchxCfw","MjyMYAXhzMT5PBaZ2"],"keywords":[],"search_terms":["umap","uniform","manifold","approximation","projection","dimension","reduction","mcinnes","healy","melville"],"title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","year":2020}