{"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/transfer-learning-for-performance-modeling-of-1","title":"Transfer Learning for Performance Modeling of Configurable Systems: An Exploratory Analysis","arxiv_id":"1709.02280","date":"2017-09-07","proceeding":null,"authors":["Pooyan Jamshidi","Norbert Siegmund","Miguel Velez","Christian Kästner","Akshay Patel","Yuvraj Agarwal"],"abstract":"Modern software systems provide many configuration options which\nsignificantly influence their non-functional properties. To understand and\npredict the effect of configuration options, several sampling and learning\nstrategies have been proposed, albeit often with significant cost to cover the\nhighly dimensional configuration space. Recently, transfer learning has been\napplied to reduce the effort of constructing performance models by transferring\nknowledge about performance behavior across environments. While this line of\nresearch is promising to learn more accurate models at a lower cost, it is\nunclear why and when transfer learning works for performance modeling. To shed\nlight on when it is beneficial to apply transfer learning, we conducted an\nempirical study on four popular software systems, varying software\nconfigurations and environmental conditions, such as hardware, workload, and\nsoftware versions, to identify the key knowledge pieces that can be exploited\nfor transfer learning. Our results show that in small environmental changes\n(e.g., homogeneous workload change), by applying a linear transformation to the\nperformance model, we can understand the performance behavior of the target\nenvironment, while for severe environmental changes (e.g., drastic workload\nchange) we can transfer only knowledge that makes sampling more efficient,\ne.g., by reducing the dimensionality of the configuration space.","url_abs":"http://arxiv.org/abs/1709.02280v1","url_pdf":"http://arxiv.org/pdf/1709.02280v1.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":"transfer-learning-for-performance-modeling-of-1","repo_url":"https://github.com/pooyanjamshidi/ase17","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}