{"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/sparse-group-bayesian-feature-selection-using","title":"Sparse-Group Bayesian Feature Selection Using Expectation Propagation for Signal Recovery and Network Reconstruction","arxiv_id":"1809.09367","date":"2018-09-25","proceeding":null,"authors":["Edgar Steiger","Martin Vingron"],"abstract":"We present a Bayesian method for feature selection in the presence of\ngrouping information with sparsity on the between- and within group level.\nInstead of using a stochastic algorithm for parameter inference, we employ\nexpectation propagation, which is a deterministic and fast algorithm. Available\nmethods for feature selection in the presence of grouping information have a\nnumber of short-comings: on one hand, lasso methods, while being fast,\nunderestimate the regression coefficients and do not make good use of the\ngrouping information, and on the other hand, Bayesian approaches, while\naccurate in parameter estimation, often rely on the stochastic and slow Gibbs\nsampling procedure to recover the parameters, rendering them infeasible e.g.\nfor gene network reconstruction. Our approach of a Bayesian sparse-group\nframework with expectation propagation enables us to not only recover accurate\nparameter estimates in signal recovery problems, but also makes it possible to\napply this Bayesian framework to large-scale network reconstruction problems.\nThe presented method is generic but in terms of application we focus on gene\nregulatory networks. We show on simulated and experimental data that the method\nconstitutes a good choice for network reconstruction regarding the number of\ncorrectly selected features, prediction on new data and reasonable computing\ntime.","url_abs":"http://arxiv.org/abs/1809.09367v1","url_pdf":"http://arxiv.org/pdf/1809.09367v1.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":"sparse-group-bayesian-feature-selection-using","repo_url":"https://github.com/edgarst/dogss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"feature-selection","task_name":"feature selection"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}