{"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/internal-node-bagging","title":"Internal node bagging","arxiv_id":"1805.00215","date":"2018-05-01","proceeding":null,"authors":["Shun Yi"],"abstract":"We introduce a novel view to understand how dropout works as an inexplicit\nensemble learning method, which doesn't point out how many and which nodes to\nlearn a certain feature. We propose a new training method named internal node\nbagging, it explicitly forces a group of nodes to learn a certain feature in\ntraining time, and combine those nodes to be one node in inference time. It\nmeans we can use much more parameters to improve model's fitting ability in\ntraining time while keeping model small in inference time. We test our method\non several benchmark datasets and find it performs significantly better than\ndropout on small models.","url_abs":"http://arxiv.org/abs/1805.00215v5","url_pdf":"http://arxiv.org/pdf/1805.00215v5.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":"internal-node-bagging","repo_url":"https://github.com/Xiong-Da/internal_node_bagging_V2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}