{"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/saas-speed-as-a-supervisor-for-semi","title":"SaaS: Speed as a Supervisor for Semi-supervised Learning","arxiv_id":"1805.00980","date":"2018-05-02","proceeding":"ECCV 2018 9","authors":["Safa Cicek","Alhussein Fawzi","Stefano Soatto"],"abstract":"We introduce the SaaS Algorithm for semi-supervised learning, which uses\nlearning speed during stochastic gradient descent in a deep neural network to\nmeasure the quality of an iterative estimate of the posterior probability of\nunknown labels. Training speed in supervised learning correlates strongly with\nthe percentage of correct labels, so we use it as an inference criterion for\nthe unknown labels, without attempting to infer the model parameters at first.\nDespite its simplicity, SaaS achieves state-of-the-art results in\nsemi-supervised learning benchmarks.","url_abs":"http://arxiv.org/abs/1805.00980v1","url_pdf":"http://arxiv.org/pdf/1805.00980v1.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":"saas-speed-as-a-supervisor-for-semi","repo_url":"https://github.com/bsafacicek/saas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}