{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:39:42Z","timestamp":1783737582550,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3485447.3512093","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T05:11:23Z","timestamp":1650863483000},"page":"2205-2215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":43,"title":["MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks"],"prefix":"10.1145","author":[{"given":"Yun","family":"He","sequence":"first","affiliation":[{"name":"Texas A&M University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Feng","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geng","family":"Ji","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunsong","family":"Guo","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Caverlee","sequence":"additional","affiliation":[{"name":"Texas A&M University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959180"},{"key":"e_1_3_2_1_2_1","volume-title":"The complexity of partial derivatives. Theoretical computer science 22, 3","author":"Baur Walter","year":"1983","unstructured":"Walter Baur and Volker Strassen. 1983. The complexity of partial derivatives. Theoretical computer science 22, 3 (1983), 317\u2013330."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Da Cao Liqiang Nie Xiangnan He Xiaochi Wei Shunzhi Zhu and Tat-Seng Chua. 2017. Embedding factorization models for jointly recommending items and user generated lists. In SIGIR.","DOI":"10.1145\/3077136.3080779"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 794\u2013803","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\u2013803."},{"key":"e_1_3_2_1_5_1","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. arXiv preprint arXiv:2010.06808(2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_7_1","unstructured":"Yunshu Du Wojciech\u00a0M Czarnecki Siddhant\u00a0M 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_8_1","volume-title":"Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research 12, 7","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization.Journal of machine learning research 12, 7 (2011)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9153"},{"key":"e_1_3_2_1_10_1","unstructured":"Xiangnan He Lizi Liao Hanwang Zhang Liqiang Nie Xia Hu and Tat-Seng Chua. 2017. Neural collaborative filtering. In WWW."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358030"},{"key":"e_1_3_2_1_12_1","unstructured":"Max Jaderberg Volodymyr Mnih Wojciech\u00a0Marian Czarnecki Tom Schaul Joel\u00a0Z Leibo David Silver and Koray Kavukcuoglu. 2016. Reinforcement learning with unsupervised auxiliary tasks. arXiv preprint arXiv:1611.05397(2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Cumulated gain-based evaluation of IR techniques. TOIS","author":"J\u00e4rvelin Kalervo","year":"2002","unstructured":"Kalervo J\u00e4rvelin and Jaana Kek\u00e4l\u00e4inen. 2002. Cumulated gain-based evaluation of IR techniques. TOIS (2002)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482\u20137491","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\u20137491."},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014)."},{"key":"e_1_3_2_1_16_1","unstructured":"Lukas Liebel and Marco K\u00f6rner. 2018. Auxiliary tasks in multi-task learning. arXiv preprint arXiv:1805.06334(2018)."},{"key":"e_1_3_2_1_17_1","unstructured":"Xingyu Lin Harjatin Baweja George Kantor and David Held. 2019. Adaptive Auxiliary Task Weighting for Reinforcement Learning. In Advances in Neural Information Processing Systems. 4772\u20134783."},{"key":"e_1_3_2_1_18_1","unstructured":"Shikun Liu Andrew Davison and Edward Johns. 2019. Self-supervised generalisation with meta auxiliary learning. In Advances in Neural Information Processing Systems. 1679\u20131689."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Yidan Liu Min Xie and Laks\u00a0VS Lakshmanan. 2014. Recommending user generated item lists. In Recsys.","DOI":"10.1145\/2645710.2645750"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458205"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Itzik Malkiel and Lior Wolf. 2020. MTAdam: Automatic Balancing of Multiple Training Loss Terms. arXiv preprint arXiv:2006.14683(2020).","DOI":"10.18653\/v1\/2021.emnlp-main.837"},{"key":"e_1_3_2_1_24_1","volume-title":"Revisiting multi-task learning with rock: a deep residual auxiliary block for visual detection. Advances in neural information processing systems 31","author":"Mordan Taylor","year":"2018","unstructured":"Taylor Mordan, Nicolas Thome, Gilles Henaff, and Matthieu Cord. 2018. Revisiting multi-task learning with rock: a deep residual auxiliary block for visual detection. Advances in neural information processing systems 31 (2018), 1310\u20131322."},{"key":"e_1_3_2_1_25_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun\u00a0Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson\u00a0G Azzolini 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091(2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"An Overview of Multi-Task Learning in Deep Neural Networks. arXiv","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder. 2017. An Overview of Multi-Task Learning in Deep Neural Networks. arXiv (2017), arXiv\u20131706."},{"key":"e_1_3_2_1_27_1","unstructured":"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_28_1","volume-title":"COURSERA: Neural Networks for Machine Learning.","author":"Tieleman T.","year":"2012","unstructured":"T. Tieleman and G. Hinton. 2012. Lecture 6.5\u2014RmsProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses. In International Conference on Machine Learning. 4965\u20134974","author":"Trinh Trieu","year":"2018","unstructured":"Trieu Trinh, Andrew Dai, Thang Luong, and Quoc Le. 2018. Learning Longer-term Dependencies in RNNs with Auxiliary Losses. In International Conference on Machine Learning. 4965\u20134974."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462979"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Simon Vandenhende Stamatios Georgoulis Wouter Van\u00a0Gansbeke Marc Proesmans Dengxin Dai and Luc Van\u00a0Gool. 2020. Multi-Task Learning for Dense Prediction Tasks: A Survey. arXiv preprint arXiv:2004.13379(2020).","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330939"},{"key":"e_1_3_2_1_34_1","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)."},{"key":"e_1_3_2_1_35_1","unstructured":"Wei Zhang Quan Yuan Jiawei Han and Jianyong Wang. 2016. Collaborative multi-Level embedding learning from reviews for rating prediction.. In IJCAI Vol.\u00a016. 2986\u20132992."}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512093","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:07Z","timestamp":1750188607000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":35,"alternative-id":["10.1145\/3485447.3512093","10.1145\/3485447"],"URL":"https:\/\/doi.org\/10.1145\/3485447.3512093","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}