{"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/predicting-computational-reproducibility-of","title":"Predicting computational reproducibility of data analysis pipelines in large population studies using collaborative filtering","arxiv_id":"1809.10139","date":"2018-09-26","proceeding":null,"authors":["Soudabeh Barghi","Lalet Scaria","Ali Salari","Tristan Glatard"],"abstract":"Evaluating the computational reproducibility of data analysis pipelines has\nbecome a critical issue. It is, however, a cumbersome process for analyses that\ninvolve data from large populations of subjects, due to their computational and\nstorage requirements. We present a method to predict the computational\nreproducibility of data analysis pipelines in large population studies. We\nformulate the problem as a collaborative filtering process, with constraints on\nthe construction of the training set. We propose 6 different strategies to\nbuild the training set, which we evaluate on 2 datasets, a synthetic one\nmodeling a population with a growing number of subject types, and a real one\nobtained with neuroinformatics pipelines. Results show that one sampling\nmethod, \"Random File Numbers (Uniform)\" is able to predict computational\nreproducibility with a good accuracy. We also analyze the relevance of\nincluding file and subject biases in the collaborative filtering model. We\nconclude that the proposed method is able to speedup reproducibility\nevaluations substantially, with a reduced accuracy loss.","url_abs":"http://arxiv.org/abs/1809.10139v1","url_pdf":"http://arxiv.org/pdf/1809.10139v1.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":"predicting-computational-reproducibility-of","repo_url":"https://github.com/big-data-lab-team/paper-reproducibility-collaborative-filtering","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}