{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:21:12Z","timestamp":1781972472199,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["23010503000"],"award-info":[{"award-number":["23010503000"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657922","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2527-2531","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["MoME: Mixture-of-Masked-Experts for Efficient Multi-Task Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9459-8289","authenticated-orcid":false,"given":"Jiahui","family":"Xu","sequence":"first","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8126-2982","authenticated-orcid":false,"given":"Lu","family":"Sun","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9572-1753","authenticated-orcid":false,"given":"Dengji","family":"Zhao","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Multitask learning. Machine learning","author":"Caruana Rich","year":"1997","unstructured":"Rich Caruana. 1997. Multitask learning. Machine learning , Vol. 28 (1997), 41--75."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463022"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"e_1_3_2_1_4_1","first-page":"29335","article-title":"Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning","volume":"34","author":"Hazimeh Hussein","year":"2021","unstructured":"Hussein Hazimeh, Zhe Zhao, Aakanksha Chowdhery, Maheswaran Sathiamoorthy, Yihua Chen, Rahul Mazumder, Lichan Hong, and Ed Chi. 2021. Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning. Advances in Neural Information Processing Systems , Vol. 34 (2021), 29335--29347.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_6_1","volume-title":"Adaptive mixtures of local experts. Neural computation","author":"Jacobs Robert A","year":"1991","unstructured":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive mixtures of local experts. Neural computation, Vol. 3, 1 (1991), 79--87."},{"key":"e_1_3_2_1_7_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Louizos Christos","year":"2018","unstructured":"Christos Louizos, Max Welling, and Diederik P Kingma. 2018. Learning Sparse Neural Networks through L_0 Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301216"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2188--2196","author":"Mnih Andriy","year":"2016","unstructured":"Andriy Mnih and Danilo Rezende. 2016. Variational inference for monte carlo objectives. In International Conference on Machine Learning. PMLR, 2188--2196."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems , Vol. 31 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_20_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning , Vol. 8 (1992), 229--256."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467071"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 10648--10659","author":"Yamada Yutaro","year":"2020","unstructured":"Yutaro Yamada, Ofir Lindenbaum, Sahand Negahban, and Yuval Kluger. 2020. Feature selection using stochastic gates. In International Conference on Machine Learning. PMLR, 10648--10659."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531942"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657922","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:23:29Z","timestamp":1755840209000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":23,"alternative-id":["10.1145\/3626772.3657922","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657922","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}