{"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/online-tensor-methods-for-learning-latent","title":"Online Tensor Methods for Learning Latent Variable Models","arxiv_id":"1309.0787","date":"2013-09-03","proceeding":null,"authors":["Furong Huang","U. N. Niranjan","Mohammad Umar Hakeem","Animashree Anandkumar"],"abstract":"We introduce an online tensor decomposition based approach for two latent\nvariable modeling problems namely, (1) community detection, in which we learn\nthe latent communities that the social actors in social networks belong to, and\n(2) topic modeling, in which we infer hidden topics of text articles. We\nconsider decomposition of moment tensors using stochastic gradient descent. We\nconduct optimization of multilinear operations in SGD and avoid directly\nforming the tensors, to save computational and storage costs. We present\noptimized algorithm in two platforms. Our GPU-based implementation exploits the\nparallelism of SIMD architectures to allow for maximum speed-up by a careful\noptimization of storage and data transfer, whereas our CPU-based implementation\nuses efficient sparse matrix computations and is suitable for large sparse\ndatasets. For the community detection problem, we demonstrate accuracy and\ncomputational efficiency on Facebook, Yelp and DBLP datasets, and for the topic\nmodeling problem, we also demonstrate good performance on the New York Times\ndataset. We compare our results to the state-of-the-art algorithms such as the\nvariational method, and report a gain of accuracy and a gain of several orders\nof magnitude in the execution time.","url_abs":"http://arxiv.org/abs/1309.0787v5","url_pdf":"http://arxiv.org/pdf/1309.0787v5.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":"online-tensor-methods-for-learning-latent","repo_url":"https://github.com/FurongHuang/Fast-Detection-of-Overlapping-Communities-via-Online-Tensor-Methods","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"community-detection","task_name":"Community Detection"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}