{"isi":1,"project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036","call_identifier":"FP7"}],"volume":70,"publist_id":"6399","intvolume":"        70","year":"2017","conference":{"start_date":"2017-08-06","name":"ICML: International Conference on Machine Learning","location":"Sydney, Australia","end_date":"2017-08-11"},"citation":{"short":"A. Pentina, C. Lampert, in:, ML Research Press, 2017, pp. 2807–2816.","chicago":"Pentina, Anastasia, and Christoph Lampert. “Multi-Task Learning with Labeled and Unlabeled Tasks,” 70:2807–16. ML Research Press, 2017.","ista":"Pentina A, Lampert C. 2017. Multi-task learning with labeled and unlabeled tasks. ICML: International Conference on Machine Learning, PMLR, vol. 70, 2807–2816.","apa":"Pentina, A., &#38; Lampert, C. (2017). Multi-task learning with labeled and unlabeled tasks (Vol. 70, pp. 2807–2816). Presented at the ICML: International Conference on Machine Learning, Sydney, Australia: ML Research Press.","ama":"Pentina A, Lampert C. Multi-task learning with labeled and unlabeled tasks. In: Vol 70. ML Research Press; 2017:2807-2816.","ieee":"A. Pentina and C. Lampert, “Multi-task learning with labeled and unlabeled tasks,” presented at the ICML: International Conference on Machine Learning, Sydney, Australia, 2017, vol. 70, pp. 2807–2816.","mla":"Pentina, Anastasia, and Christoph Lampert. <i>Multi-Task Learning with Labeled and Unlabeled Tasks</i>. Vol. 70, ML Research Press, 2017, pp. 2807–16."},"ec_funded":1,"_id":"999","language":[{"iso":"eng"}],"author":[{"id":"42E87FC6-F248-11E8-B48F-1D18A9856A87","full_name":"Pentina, Anastasia","first_name":"Anastasia","last_name":"Pentina"},{"first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"page":"2807 - 2816","publication_identifier":{"isbn":["9781510855144"]},"external_id":{"isi":["000683309502093"]},"status":"public","quality_controlled":"1","title":"Multi-task learning with labeled and unlabeled tasks","alternative_title":["PMLR"],"date_created":"2018-12-11T11:49:37Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Submitted Version","oa":1,"scopus_import":"1","publisher":"ML Research Press","publication_status":"published","date_published":"2017-06-08T00:00:00Z","abstract":[{"lang":"eng","text":"In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data must be available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided. Consequently, to solve all tasks, information must be transferred between tasks with labels and tasks without labels. Focusing on an instance-based transfer method we analyze two variants of this setting: when the set of labeled tasks is fixed, and when it can be actively selected by the learner. We state and prove a generalization bound that covers both scenarios and derive from it an algorithm for making the choice of labeled tasks (in the active case) and for transferring information between the tasks in a principled way. We also illustrate the effectiveness of the algorithm on synthetic and real data. "}],"main_file_link":[{"url":"https://arxiv.org/abs/1602.06518","open_access":"1"}],"department":[{"_id":"ChLa"}],"day":"08","type":"conference","date_updated":"2023-10-17T11:53:32Z","article_processing_charge":"No","month":"06"}