{"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/a-two-step-learning-approach-for-solving-full","title":"A two-step learning approach for solving full and almost full cold start problems in dyadic prediction","arxiv_id":"1405.4423","date":"2014-05-17","proceeding":null,"authors":["Tapio Pahikkala","Michiel Stock","Antti Airola","Tero Aittokallio","Bernard De Baets","Willem Waegeman"],"abstract":"Dyadic prediction methods operate on pairs of objects (dyads), aiming to\ninfer labels for out-of-sample dyads. We consider the full and almost full cold\nstart problem in dyadic prediction, a setting that occurs when both objects in\nan out-of-sample dyad have not been observed during training, or if one of them\nhas been observed, but very few times. A popular approach for addressing this\nproblem is to train a model that makes predictions based on a pairwise feature\nrepresentation of the dyads, or, in case of kernel methods, based on a tensor\nproduct pairwise kernel. As an alternative to such a kernel approach, we\nintroduce a novel two-step learning algorithm that borrows ideas from the\nfields of pairwise learning and spectral filtering. We show theoretically that\nthe two-step method is very closely related to the tensor product kernel\napproach, and experimentally that it yields a slightly better predictive\nperformance. Moreover, unlike existing tensor product kernel methods, the\ntwo-step method allows closed-form solutions for training and parameter\nselection via cross-validation estimates both in the full and almost full cold\nstart settings, making the approach much more efficient and straightforward to\nimplement.","url_abs":"http://arxiv.org/abs/1405.4423v1","url_pdf":"http://arxiv.org/pdf/1405.4423v1.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":"a-two-step-learning-approach-for-solving-full","repo_url":"https://github.com/aatapa/RLScore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}