{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:17:54Z","timestamp":1775200674438,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,17]]},"DOI":"10.1145\/3511808.3557333","type":"proceedings-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:22:22Z","timestamp":1665883342000},"page":"386-395","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["GDOD"],"prefix":"10.1145","author":[{"given":"Xin","family":"Dong","sequence":"first","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruize","family":"Wu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Xiong","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"He","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyou","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjian","family":"Mo","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"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 , 1 ( 1997 ), 41--75. Rich Caruana. 1997. Multitask learning. Machine learning, Vol. 28, 1 (1997), 41--75."},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 794--803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen , Vijay Badrinarayanan , Chen-Yu Lee , and Andrew Rabinovich . 2018 . Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks . In International Conference on Machine Learning. PMLR, 794--803 . Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International Conference on Machine Learning. PMLR, 794--803."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"e_1_3_2_1_6_1","volume-title":"Adapting auxiliary losses using gradient similarity. arXiv preprint arXiv:1812.02224","author":"Du Yunshu","year":"2018","unstructured":"Yunshu Du , Wojciech M Czarnecki , Siddhant M Jayakumar , Mehrdad Farajtabar , Razvan Pascanu , and Balaji Lakshminarayanan . 2018. Adapting auxiliary losses using gradient similarity. arXiv preprint arXiv:1812.02224 ( 2018 ). Yunshu Du, Wojciech M Czarnecki, Siddhant M Jayakumar, Mehrdad Farajtabar, Razvan Pascanu, and Balaji Lakshminarayanan. 2018. Adapting auxiliary losses using gradient similarity. arXiv preprint arXiv:1812.02224 (2018)."},{"key":"e_1_3_2_1_7_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017).  Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_8_1","series-title":"SIAM review","volume-title":"Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions","author":"Halko Nathan","year":"2011","unstructured":"Nathan Halko , Per-Gunnar Martinsson , and Joel A Tropp . 2011. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions . SIAM review , Vol. 53 , 2 ( 2011 ), 217--288. Nathan Halko, Per-Gunnar Martinsson, and Joel A Tropp. 2011. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM review, Vol. 53, 2 (2011), 217--288."},{"key":"e_1_3_2_1_9_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. 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_10_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall , Yarin Gal , and Roberto Cipolla . 2018 . Multi-task learning using uncertainty to weigh losses for scene geometry and semantics . In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491 . Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491."},{"key":"e_1_3_2_1_11_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). 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_12_1","unstructured":"Kohavi R. Lane T. 2010. Census-Income (KDD) dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Census-Income(KDD).  Kohavi R. Lane T. 2010. Census-Income (KDD) dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Census-Income(KDD)."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Liu Bo","year":"2021","unstructured":"Bo Liu , Xingchao Liu , Xiaojie Jin , Peter Stone , and Qiang Liu . 2021 . Conflict-Averse Gradient Descent for Multi-task Learning . Advances in Neural Information Processing Systems , Vol. 34 (2021). Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, and Qiang Liu. 2021. Conflict-Averse Gradient Descent for Multi-task Learning. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1871--1880","author":"Liu Shikun","unstructured":"Shikun Liu , Edward Johns , and Andrew J. Davison . 2019a. End-to-end multi-task learning with attention . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1871--1880 . Shikun Liu, Edward Johns, and Andrew J. Davison. 2019a. End-to-end multi-task learning with attention. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1871--1880."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019977"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301216"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_18_1","unstructured":"Krzysztof Maziarz Efi Kokiopoulou Andrea Gesmundo Luciano Sbaiz Gabor Bartok and Jesse Berent. 2019. Gumbel-matrix routing for flexible multi-task learning. (2019).  Krzysztof Maziarz Efi Kokiopoulou Andrea Gesmundo Luciano Sbaiz Gabor Bartok and Jesse Berent. 2019. Gumbel-matrix routing for flexible multi-task learning. (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Coresets for robust training of neural networks against noisy labels. arXiv preprint arXiv:2011.07451","author":"Mirzasoleiman Baharan","year":"2020","unstructured":"Baharan Mirzasoleiman , Kaidi Cao , and Jure Leskovec . 2020. Coresets for robust training of neural networks against noisy labels. arXiv preprint arXiv:2011.07451 ( 2020 ). Baharan Mirzasoleiman, Kaidi Cao, and Jure Leskovec. 2020. Coresets for robust training of neural networks against noisy labels. arXiv preprint arXiv:2011.07451 (2020)."},{"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","volume-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910","author":"Riemer Matthew","year":"2018","unstructured":"Matthew Riemer , Ignacio Cases , Robert Ajemian , Miao Liu , Irina Rish , Yuhai Tu , and Gerald Tesauro . 2018. Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 ( 2018 ). Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro. 2018. Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)."},{"key":"e_1_3_2_1_22_1","volume-title":"Routing networks: Adaptive selection of non-linear functions for multi-task learning. arXiv preprint arXiv:1711.01239","author":"Rosenbaum Clemens","year":"2017","unstructured":"Clemens Rosenbaum , Tim Klinger , and Matthew Riemer . 2017. Routing networks: Adaptive selection of non-linear functions for multi-task learning. arXiv preprint arXiv:1711.01239 ( 2017 ). Clemens Rosenbaum, Tim Klinger, and Matthew Riemer. 2017. Routing networks: Adaptive selection of non-linear functions for multi-task learning. arXiv preprint arXiv:1711.01239 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder . 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 ( 2017 ). Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"Sluice networks: Learning what to share between loosely related tasks. arXiv preprint arXiv:1705.08142","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder , Joachim Bingel , Isabelle Augenstein , and Anders S\u00f8gaard . 2017. Sluice networks: Learning what to share between loosely related tasks. arXiv preprint arXiv:1705.08142 , Vol. 2 ( 2017 ). Sebastian Ruder, Joachim Bingel, Isabelle Augenstein, and Anders S\u00f8gaard. 2017. Sluice networks: Learning what to share between loosely related tasks. arXiv preprint arXiv:1705.08142, Vol. 2 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Multi-task learning as multi-objective optimization. arXiv preprint arXiv:1810.04650","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun . 2018. Multi-task learning as multi-objective optimization. arXiv preprint arXiv:1810.04650 ( 2018 ). Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. arXiv preprint arXiv:1810.04650 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 9120--9132","author":"Standley Trevor","year":"2020","unstructured":"Trevor Standley , Amir Zamir , Dawn Chen , Leonidas Guibas , Jitendra Malik , and Silvio Savarese . 2020 . Which tasks should be learned together in multi-task learning? . In International Conference on Machine Learning. PMLR, 9120--9132 . Trevor Standley, Amir Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, and Silvio Savarese. 2020. Which tasks should be learned together in multi-task learning?. In International Conference on Machine Learning. PMLR, 9120--9132."},{"key":"e_1_3_2_1_28_1","volume-title":"Learning general purpose distributed sentence representations via large scale multi-task learning. arXiv preprint arXiv:1804.00079","author":"Subramanian Sandeep","year":"2018","unstructured":"Sandeep Subramanian , Adam Trischler , Yoshua Bengio , and Christopher J Pal . 2018. Learning general purpose distributed sentence representations via large scale multi-task learning. arXiv preprint arXiv:1804.00079 ( 2018 ). Sandeep Subramanian, Adam Trischler, Yoshua Bengio, and Christopher J Pal. 2018. Learning general purpose distributed sentence representations via large scale multi-task learning. arXiv preprint arXiv:1804.00079 (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"Regularizing deep multi-task networks using orthogonal gradients. arXiv preprint arXiv:1912.06844","author":"Suteu Mihai","year":"2019","unstructured":"Mihai Suteu and Yike Guo . 2019. Regularizing deep multi-task networks using orthogonal gradients. arXiv preprint arXiv:1912.06844 ( 2019 ). Mihai Suteu and Yike Guo. 2019. Regularizing deep multi-task networks using orthogonal gradients. arXiv preprint arXiv:1912.06844 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_31_1","unstructured":"Michael Wooldridge and Qiang Yang. 2015. IJCAI-15 dataset. https:\/\/ijcai-15.org\/repeat-buyers-prediction-competition\/.  Michael Wooldridge and Qiang Yang. 2015. IJCAI-15 dataset. https:\/\/ijcai-15.org\/repeat-buyers-prediction-competition\/."},{"key":"e_1_3_2_1_32_1","volume-title":"Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu , Saurabh Kumar , Abhishek Gupta , Sergey Levine , Karol Hausman , and Chelsea Finn . 2020. Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782 ( 2020 ). Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782 (2020)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330861"},{"key":"e_1_3_2_1_35_1","unstructured":"Freiburg Ziegler C.N. 2004. BookCrossing dataset. http:\/\/www2.informatik.uni-freiburg.de\/ cziegler\/BX\/.  Freiburg Ziegler C.N. 2004. BookCrossing dataset. http:\/\/www2.informatik.uni-freiburg.de\/ cziegler\/BX\/."},{"key":"e_1_3_2_1_36_1","volume-title":"Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578","author":"Zoph Barret","year":"2016","unstructured":"Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 ( 2016 ). Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)."}],"event":{"name":"CIKM '22: The 31st ACM International Conference on Information and Knowledge Management","location":"Atlanta GA USA","acronym":"CIKM '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 31st ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557333","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:29Z","timestamp":1750182569000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557333"}},"subtitle":["Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning"],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":35,"alternative-id":["10.1145\/3511808.3557333","10.1145\/3511808"],"URL":"https:\/\/doi.org\/10.1145\/3511808.3557333","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}