{"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/dual-supervised-learning","title":"Dual Supervised Learning","arxiv_id":"1707.00415","date":"2017-07-03","proceeding":"ICML 2017 8","authors":["Yingce Xia","Tao Qin","Wei Chen","Jiang Bian","Nenghai Yu","Tie-Yan Liu"],"abstract":"Many supervised learning tasks are emerged in dual forms, e.g.,\nEnglish-to-French translation vs. French-to-English translation, speech\nrecognition vs. text to speech, and image classification vs. image generation.\nTwo dual tasks have intrinsic connections with each other due to the\nprobabilistic correlation between their models. This connection is, however,\nnot effectively utilized today, since people usually train the models of two\ndual tasks separately and independently. In this work, we propose training the\nmodels of two dual tasks simultaneously, and explicitly exploiting the\nprobabilistic correlation between them to regularize the training process. For\nease of reference, we call the proposed approach \\emph{dual supervised\nlearning}. We demonstrate that dual supervised learning can improve the\npractical performances of both tasks, for various applications including\nmachine translation, image processing, and sentiment analysis.","url_abs":"http://arxiv.org/abs/1707.00415v1","url_pdf":"http://arxiv.org/pdf/1707.00415v1.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":"dual-supervised-learning","repo_url":"https://github.com/kh-kim/simple-nmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.00415","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}