{"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/consistencies-and-inconsistencies-between","title":"Consistencies and inconsistencies between model selection and link prediction in networks","arxiv_id":"1705.07967","date":"2017-05-22","proceeding":null,"authors":["Toni Vallès-Català","Tiago P. Peixoto","Roger Guimerà","Marta Sales-Pardo"],"abstract":"A principled approach to understand network structures is to formulate\ngenerative models. Given a collection of models, however, an outstanding key\ntask is to determine which one provides a more accurate description of the\nnetwork at hand, discounting statistical fluctuations. This problem can be\napproached using two principled criteria that at first may seem equivalent:\nselecting the most plausible model in terms of its posterior probability; or\nselecting the model with the highest predictive performance in terms of\nidentifying missing links. Here we show that while these two approaches yield\nconsistent results in most of cases, there are also notable instances where\nthey do not, that is, where the most plausible model is not the most\npredictive. We show that in the latter case the improvement of predictive\nperformance can in fact lead to overfitting both in artificial and empirical\nsettings. Furthermore, we show that, in general, the predictive performance is\nhigher when we average over collections of models that are individually less\nplausible, than when we consider only the single most plausible model.","url_abs":"http://arxiv.org/abs/1705.07967v2","url_pdf":"http://arxiv.org/pdf/1705.07967v2.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":"consistencies-and-inconsistencies-between","repo_url":"https://git.skewed.de/count0/graph-tool","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}