{"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/regularization-learning-networks-deep","title":"Regularization Learning Networks: Deep Learning for Tabular Datasets","arxiv_id":"1805.06440","date":"2018-05-16","proceeding":"NeurIPS 2018 12","authors":["Ira Shavitt","Eran Segal"],"abstract":"Despite their impressive performance, Deep Neural Networks (DNNs) typically\nunderperform Gradient Boosting Trees (GBTs) on many tabular-dataset learning\ntasks. We propose that applying a different regularization coefficient to each\nweight might boost the performance of DNNs by allowing them to make more use of\nthe more relevant inputs. However, this will lead to an intractable number of\nhyperparameters. Here, we introduce Regularization Learning Networks (RLNs),\nwhich overcome this challenge by introducing an efficient hyperparameter tuning\nscheme which minimizes a new Counterfactual Loss. Our results show that RLNs\nsignificantly improve DNNs on tabular datasets, and achieve comparable results\nto GBTs, with the best performance achieved with an ensemble that combines GBTs\nand RLNs. RLNs produce extremely sparse networks, eliminating up to 99.8% of\nthe network edges and 82% of the input features, thus providing more\ninterpretable models and reveal the importance that the network assigns to\ndifferent inputs. RLNs could efficiently learn a single network in datasets\nthat comprise both tabular and unstructured data, such as in the setting of\nmedical imaging accompanied by electronic health records. An open source\nimplementation of RLN can be found at\nhttps://github.com/irashavitt/regularization_learning_networks.","url_abs":"http://arxiv.org/abs/1805.06440v3","url_pdf":"http://arxiv.org/pdf/1805.06440v3.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":"regularization-learning-networks-deep","repo_url":"https://github.com/irashavitt/regularization_learning_networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}