{"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/deep-asymmetric-multi-task-feature-learning","title":"Deep Asymmetric Multi-task Feature Learning","arxiv_id":"1708.00260","date":"2017-08-01","proceeding":"ICML 2018 7","authors":["Hae Beom Lee","Eunho Yang","Sung Ju Hwang"],"abstract":"We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can\nlearn deep representations shared across multiple tasks while effectively\npreventing negative transfer that may happen in the feature sharing process.\nSpecifically, we introduce an asymmetric autoencoder term that allows reliable\npredictors for the easy tasks to have high contribution to the feature learning\nwhile suppressing the influences of unreliable predictors for more difficult\ntasks. This allows the learning of less noisy representations, and enables\nunreliable predictors to exploit knowledge from the reliable predictors via the\nshared latent features. Such asymmetric knowledge transfer through shared\nfeatures is also more scalable and efficient than inter-task asymmetric\ntransfer. We validate our Deep-AMTFL model on multiple benchmark datasets for\nmultitask learning and image classification, on which it significantly\noutperforms existing symmetric and asymmetric multitask learning models, by\neffectively preventing negative transfer in deep feature learning.","url_abs":"http://arxiv.org/abs/1708.00260v3","url_pdf":"http://arxiv.org/pdf/1708.00260v3.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":"deep-asymmetric-multi-task-feature-learning","repo_url":"https://github.com/haebeom-lee/amtfl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1708.00260","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}