{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/visualizing-large-scale-and-high-dimensional","title":"Visualizing Large-scale and High-dimensional Data","arxiv_id":"1602.00370","date":"2016-02-01","proceeding":null,"authors":["Jian Tang","Jingzhou Liu","Ming Zhang","Qiaozhu Mei"],"abstract":"We study the problem of visualizing large-scale and high-dimensional data in\na low-dimensional (typically 2D or 3D) space. Much success has been reported\nrecently by techniques that first compute a similarity structure of the data\npoints and then project them into a low-dimensional space with the structure\npreserved. These two steps suffer from considerable computational costs,\npreventing the state-of-the-art methods such as the t-SNE from scaling to\nlarge-scale and high-dimensional data (e.g., millions of data points and\nhundreds of dimensions). We propose the LargeVis, a technique that first\nconstructs an accurately approximated K-nearest neighbor graph from the data\nand then layouts the graph in the low-dimensional space. Comparing to t-SNE,\nLargeVis significantly reduces the computational cost of the graph construction\nstep and employs a principled probabilistic model for the visualization step,\nthe objective of which can be effectively optimized through asynchronous\nstochastic gradient descent with a linear time complexity. The whole procedure\nthus easily scales to millions of high-dimensional data points. Experimental\nresults on real-world data sets demonstrate that the LargeVis outperforms the\nstate-of-the-art methods in both efficiency and effectiveness. The\nhyper-parameters of LargeVis are also much more stable over different data\nsets.","url_abs":"http://arxiv.org/abs/1602.00370v2","url_pdf":"http://arxiv.org/pdf/1602.00370v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"visualizing-large-scale-and-high-dimensional","repo_url":"https://github.com/LiuChuang0059/Complex-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visualizing-large-scale-and-high-dimensional","repo_url":"https://github.com/elbamos/largeVis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"visualizing-large-scale-and-high-dimensional","repo_url":"https://github.com/jlmelville/uwot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"visualizing-large-scale-and-high-dimensional","repo_url":"https://github.com/lferry007/LargeVis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visualizing-large-scale-and-high-dimensional","repo_url":"https://github.com/mevers/animated_dimensionality_reduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.00370","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}