{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:14:12Z","timestamp":1772774052242,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CNS-1815619"],"award-info":[{"award-number":["CNS-1815619"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482432","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:31:13Z","timestamp":1636990273000},"page":"322-331","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["FiShNet: Fine-Grained Filter Sharing for Resource-Efficient Multi-Task Learning"],"prefix":"10.1145","author":[{"given":"Xin","family":"Dai","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"Kong","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Guo","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinlu","family":"He","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007327622663"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. 4th Int. Conf. Learning Representations (ICLR'16)","author":"Bengio Emmanuel","year":"2015","unstructured":"Emmanuel Bengio , Pierre-Luc Bacon , Joelle Pineau , and Doina Precup . Conditional computation in neural networks for faster models . In Proc. 4th Int. Conf. Learning Representations (ICLR'16) Workshop , 2015 . Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, and Doina Precup. Conditional computation in neural networks for faster models. In Proc. 4th Int. Conf. Learning Representations (ICLR'16) Workshop, 2015."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00147"},{"key":"e_1_3_2_1_4_1","first-page":"1153","volume-title":"Proc. 37th Int. Conf. Machine Learning (ICML'20)","author":"Bronskill John","year":"2020","unstructured":"John Bronskill , Jonathan Gordon , James Requeima , Sebastian Nowozin , and Richard Turner . Tasknorm : Rethinking batch normalization for meta-learning . In Proc. 37th Int. Conf. Machine Learning (ICML'20) , pages 1153 -- 1164 . PMLR, 2020 . John Bronskill, Jonathan Gordon, James Requeima, Sebastian Nowozin, and Richard Turner. Tasknorm: Rethinking batch normalization for meta-learning. In Proc. 37th Int. Conf. Machine Learning (ICML'20), pages 1153--1164. PMLR, 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_1_6_1","first-page":"9282","volume-title":"Proc. 2020 IEEE Conf. Computer Vision and Pattern Recognition (CVPR'20)","author":"Davidson Guy","year":"2020","unstructured":"Guy Davidson and Michael C Mozer . Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget . In Proc. 2020 IEEE Conf. Computer Vision and Pattern Recognition (CVPR'20) , pages 9282 -- 9293 , 2020 . Guy Davidson and Michael C Mozer. Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget. In Proc. 2020 IEEE Conf. Computer Vision and Pattern Recognition (CVPR'20), pages 9282--9293, 2020."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01156"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"e_1_3_2_1_10_1","first-page":"3854","volume-title":"Proc. 37th Int. Conf. Machine Learning (ICML'20)","author":"Guo Pengsheng","year":"2020","unstructured":"Pengsheng Guo , Chen-Yu Lee , and Daniel Ulbricht . Learning to branch for multi-task learning . In Proc. 37th Int. Conf. Machine Learning (ICML'20) , pages 3854 -- 3863 . PMLR, 2020 . Pengsheng Guo, Chen-Yu Lee, and Daniel Ulbricht. Learning to branch for multi-task learning. In Proc. 37th Int. Conf. Machine Learning (ICML'20), pages 3854--3863. PMLR, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330974"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_13_1","first-page":"448","volume-title":"Proc. 32nd Int. Conf. Machine Learning (ICML'15)","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . Batch normalization : Accelerating deep network training by reducing internal covariate shift . In Proc. 32nd Int. Conf. Machine Learning (ICML'15) , pages 448 -- 456 , 2015 . Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proc. 32nd Int. Conf. Machine Learning (ICML'15), pages 448--456, 2015."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. 5th Int. Conf. Learning Representations (ICLR'17)","author":"Jang Eric","year":"2017","unstructured":"Eric Jang , Shixiang Gu , and Ben Poole . Categorical reparameterization with gumbel-softmax . In Proc. 5th Int. Conf. Learning Representations (ICLR'17) , 2017 . Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. In Proc. 5th Int. Conf. Learning Representations (ICLR'17), 2017."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"e_1_3_2_1_16_1","volume-title":"Multi-task learning by a top-down control network. arXiv preprint arXiv:2002.03335","author":"Levi Hila","year":"2020","unstructured":"Hila Levi and Shimon Ullman . Multi-task learning by a top-down control network. arXiv preprint arXiv:2002.03335 , 2020 . Hila Levi and Shimon Ullman. Multi-task learning by a top-down control network. arXiv preprint arXiv:2002.03335, 2020."},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. 7th Int. Conf. Learning Representations (ICLR'19)","author":"Liu Hanxiao","year":"2019","unstructured":"Hanxiao Liu , Karen Simonyan , and Yiming Yang . Darts : Differentiable architecture search . In Proc. 7th Int. Conf. Learning Representations (ICLR'19) , 2019 . Hanxiao Liu, Karen Simonyan, and Yiming Yang. Darts: Differentiable architecture search. In Proc. 7th Int. Conf. Learning Representations (ICLR'19), 2019."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_21_1","first-page":"2204","volume-title":"Advances in Neural Information Processing Systems 27 (NeurIPS'14)","author":"Mnih Volodymyr","year":"2014","unstructured":"Volodymyr Mnih , Nicolas Heess , Alex Graves , Recurrent models of visual attention . In Advances in Neural Information Processing Systems 27 (NeurIPS'14) , pages 2204 -- 2212 , 2014 . Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. Recurrent models of visual attention. In Advances in Neural Information Processing Systems 27 (NeurIPS'14), pages 2204--2212, 2014."},{"key":"e_1_3_2_1_22_1","first-page":"9120","volume-title":"Proc. 37th Int. Conf. Machine Learning (ICML'20)","author":"Standley Trevor","year":"2020","unstructured":"Trevor Standley , Amir Zamir , Dawn Chen , Leonidas Guibas , Jitendra Malik , and Silvio Savarese . Which tasks should be learned together in multi-task learning? In Proc. 37th Int. Conf. Machine Learning (ICML'20) , pages 9120 -- 9132 . PMLR, 2020 . Trevor Standley, Amir Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, and Silvio Savarese. Which tasks should be learned together in multi-task learning? In Proc. 37th Int. Conf. Machine Learning (ICML'20), pages 9120--9132. PMLR, 2020."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00146"},{"key":"e_1_3_2_1_24_1","volume-title":"Adashare: Learning what to share for efficient deep multi-task learning. arXiv preprint arXiv:1911.12423","author":"Sun Ximeng","year":"2019","unstructured":"Ximeng Sun , Rameswar Panda , Rogerio Feris , and Kate Saenko . Adashare: Learning what to share for efficient deep multi-task learning. arXiv preprint arXiv:1911.12423 , 2019 . Ximeng Sun, Rameswar Panda, Rogerio Feris, and Kate Saenko. Adashare: Learning what to share for efficient deep multi-task learning. arXiv preprint arXiv:1911.12423, 2019."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"e_1_3_2_1_28_1","volume-title":"A survey on multi-task learning. arXiv preprint arXiv:1707.08114","author":"Zhang Yu","year":"2017","unstructured":"Yu Zhang and Qiang Yang . A survey on multi-task learning. arXiv preprint arXiv:1707.08114 , 2017 . Yu Zhang and Qiang Yang. A survey on multi-task learning. arXiv preprint arXiv:1707.08114, 2017."}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","location":"Virtual Event Queensland Australia","acronym":"CIKM '21","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482432","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482432","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:23Z","timestamp":1750191143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":28,"alternative-id":["10.1145\/3459637.3482432","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482432","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}