{"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/cardinality-estimation-in-a-virtualized","title":"Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning","arxiv_id":"1903.05728","date":"2019-03-13","proceeding":null,"authors":["Reuven Cohen","Yuval Nezri"],"abstract":"Cardinality estimation algorithms receive a stream of elements, with possible\nrepetitions, and return the number of distinct elements in the stream. Such\nalgorithms seek to minimize the required memory and CPU resource consumption at\nthe price of inaccuracy in their output. In computer networks, cardinality\nestimation algorithms are mainly used for counting the number of distinct\nflows, and they are divided into two categories: sketching algorithms and\nsampling algorithms. Sketching algorithms require the processing of all\npackets, and they are therefore usually implemented by dedicated hardware.\nSampling algorithms do not require processing of all packets, but they are\nknown for their inaccuracy. In this work we identify one of the major drawbacks\nof sampling-based cardinality estimation algorithms: their inability to adapt\nto changes in flow size distribution. To address this problem, we propose a new\nsampling-based adaptive cardinality estimation framework, which uses online\nmachine learning. We evaluate our framework using real traffic traces, and show\nsignificantly better accuracy compared to the best known sampling-based\nalgorithms, for the same fraction of processed packets.","url_abs":"http://arxiv.org/abs/1903.05728v1","url_pdf":"http://arxiv.org/pdf/1903.05728v1.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":"cardinality-estimation-in-a-virtualized","repo_url":"https://github.com/yuvalnezri/CardEst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"CPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}