{"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/learning-to-learn-from-weak-supervision-by","title":"Learning to Learn from Weak Supervision by Full Supervision","arxiv_id":"1711.11383","date":"2017-11-30","proceeding":null,"authors":["Mostafa Dehghani","Aliaksei Severyn","Sascha Rothe","Jaap Kamps"],"abstract":"In this paper, we propose a method for training neural networks when we have\na large set of data with weak labels and a small amount of data with true\nlabels. In our proposed model, we train two neural networks: a target network,\nthe learner and a confidence network, the meta-learner. The target network is\noptimized to perform a given task and is trained using a large set of unlabeled\ndata that are weakly annotated. We propose to control the magnitude of the\ngradient updates to the target network using the scores provided by the second\nconfidence network, which is trained on a small amount of supervised data. Thus\nwe avoid that the weight updates computed from noisy labels harm the quality of\nthe target network model.","url_abs":"http://arxiv.org/abs/1711.11383v1","url_pdf":"http://arxiv.org/pdf/1711.11383v1.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":"learning-to-learn-from-weak-supervision-by","repo_url":"https://github.com/krayush07/learn-by-weak-supervision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11383","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}