{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:42:35Z","timestamp":1777653755826,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"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":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703503","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:33:36Z","timestamp":1740573216000},"page":"204-212","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6961-7432","authenticated-orcid":false,"given":"Shijie","family":"Zhu","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8496-3629","authenticated-orcid":false,"given":"Hui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1023-4564","authenticated-orcid":false,"given":"Tianshu","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4285-5033","authenticated-orcid":false,"given":"Pengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9659-5111","authenticated-orcid":false,"given":"Hongbo","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3111-1005","authenticated-orcid":false,"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4037-6315","authenticated-orcid":false,"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan Vijay","year":"2017","unstructured":"Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 12 (2017), 2481--2495."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512043"},{"key":"e_1_3_2_1_3_1","volume-title":"Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420","author":"Chaudhry Arslan","year":"2018","unstructured":"Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. 2018. Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420 (2018)."},{"key":"e_1_3_2_1_4_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."},{"key":"e_1_3_2_1_5_1","first-page":"2039","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","volume":"33","author":"Chen Zhao","year":"2020","unstructured":"Zhao Chen, Jiquan Ngiam, Yanping Huang, Thang Luong, Henrik Kretzschmar, Yuning Chai, and Dragomir Anguelov. 2020. Just pick a sign: Optimizing deep multitask models with gradient sign dropout. Advances in Neural Information Processing Systems, Vol. 33 (2020), 2039--2050.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.na.2011.04.067"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1166"},{"key":"e_1_3_2_1_9_1","volume-title":"A projected gradient method for vector optimization problems. Computational Optimization and applications","author":"Drummond LM","year":"2004","unstructured":"LM Drummond and Alfredo N Iusem. 2004. A projected gradient method for vector optimization problems. Computational Optimization and applications, Vol. 28, 1 (2004), 5--29."},{"key":"e_1_3_2_1_10_1","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3762--3773","author":"Farajtabar Mehrdad","year":"2020","unstructured":"Mehrdad Farajtabar, Navid Azizan, Alex Mott, and Ang Li. 2020. Orthogonal gradient descent for continual learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 3762--3773."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"e_1_3_2_1_13_1","volume-title":"Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580","author":"Hinton Geoffrey E","year":"2012","unstructured":"Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)."},{"key":"e_1_3_2_1_14_1","volume-title":"RotoGrad: Gradient Homogenization in Multitask Learning. International Conference on Learning Representations","author":"Javaloy Adri\u00e1n","year":"2022","unstructured":"Adri\u00e1n Javaloy and Isabel Valera. 2022. RotoGrad: Gradient Homogenization in Multitask Learning. International Conference on Learning Representations (2022)."},{"key":"e_1_3_2_1_15_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."},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"e_1_3_2_1_18_1","volume-title":"LibMTL: A Python Library for Multi-Task Learning. arXiv preprint arXiv:2203.14338","author":"Lin Baijiong","year":"2022","unstructured":"Baijiong Lin and Yu Zhang. 2022. LibMTL: A Python Library for Multi-Task Learning. arXiv preprint arXiv:2203.14338 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346998"},{"key":"e_1_3_2_1_20_1","volume-title":"Pareto multi-task learning. Advances in neural information processing systems","author":"Lin Xi","year":"2019","unstructured":"Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qing-Fu Zhang, and Sam Kwong. 2019b. Pareto multi-task learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_21_1","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume":"34","author":"Liu Bo","year":"2021","unstructured":"Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, and Qiang Liu. 2021b. Conflict-averse gradient descent for multi-task learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18878--18890.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Learning Representations.","author":"Liu Liyang","year":"2021","unstructured":"Liyang Liu, Yi Li, Zhanghui Kuang, J Xue, Yimin Chen, Wenming Yang, Qingmin Liao, and Wayne Zhang. 2021a. Towards impartial multi-task learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_1_24_1","volume-title":"Gradient episodic memory for continual learning. Advances in neural information processing systems","author":"Lopez-Paz David","year":"2017","unstructured":"David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 6597--6607","author":"Mahapatra Debabrata","year":"2020","unstructured":"Debabrata Mahapatra and Vaibhav Rajan. 2020. Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization. In International Conference on Machine Learning. PMLR, 6597--6607."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"e_1_3_2_1_29_1","volume-title":"Caiming Xiong, and Richard Socher.","author":"McCann Bryan","year":"2018","unstructured":"Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, and Richard Socher. 2018. The natural language decathlon: Multitask learning as question answering. arXiv preprint arXiv:1806.08730 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning","author":"Navon Aviv","year":"2022","unstructured":"Aviv Navon, Aviv Shamsian, Idan Achituve, Haggai Maron, Kenji Kawaguchi, Gal Chechik, and Ethan Fetaya. 2022. Multi-task learning as a bargaining game. International Conference on Machine Learning (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Learning the Pareto Front with Hypernetworks. In International Conference on Learning Representations.","author":"Navon Aviv","year":"2021","unstructured":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, and Gal Chechik. 2021. Learning the Pareto Front with Hypernetworks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_34_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_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_37_1","volume-title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models. In International Conference on Learning Representations.","author":"Wang Zirui","year":"2020","unstructured":"Zirui Wang, Yulia Tsvetkov, Orhan Firat, and Yuan Cao. 2020. Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401443"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467071"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269285"},{"key":"e_1_3_2_1_41_1","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","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. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5824--5836.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","location":"Hannover Germany","acronym":"WSDM '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703503","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:16:19Z","timestamp":1755767779000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703503"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":42,"alternative-id":["10.1145\/3701551.3703503","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703503","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}