{"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/adversarial-dropout-for-recurrent-neural","title":"Adversarial Dropout for Recurrent Neural Networks","arxiv_id":"1904.09816","date":"2019-04-22","proceeding":null,"authors":["Sungrae Park","Kyungwoo Song","Mingi Ji","Wonsung Lee","Il-Chul Moon"],"abstract":"Successful application processing sequential data, such as text and speech,\nrequires an improved generalization performance of recurrent neural networks\n(RNNs). Dropout techniques for RNNs were introduced to respond to these\ndemands, but we conjecture that the dropout on RNNs could have been improved by\nadopting the adversarial concept. This paper investigates ways to improve the\ndropout for RNNs by utilizing intentionally generated dropout masks.\nSpecifically, the guided dropout used in this research is called as adversarial\ndropout, which adversarially disconnects neurons that are dominantly used to\npredict correct targets over time. Our analysis showed that our regularizer,\nwhich consists of a gap between the original and the reconfigured RNNs, was the\nupper bound of the gap between the training and the inference phases of the\nrandom dropout. We demonstrated that minimizing our regularizer improved the\neffectiveness of the dropout for RNNs on sequential MNIST tasks,\nsemi-supervised text classification tasks, and language modeling tasks.","url_abs":"http://arxiv.org/abs/1904.09816v1","url_pdf":"http://arxiv.org/pdf/1904.09816v1.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":"adversarial-dropout-for-recurrent-neural","repo_url":"https://github.com/sungraepark/AdvDrop-sMNIST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"adversarial-dropout-for-recurrent-neural","repo_url":"https://github.com/sungraepark/adversarial_dropout_text_classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"semi-supervised-text-classification-1","task_name":"Semi-Supervised Text Classification"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"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}