{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:23Z","timestamp":1784138723099,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808413","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"5038-5043","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SCOPE: Scalable Cross-Task Orthogonal Progressive Experts for Multi-Task Learning in Recommendations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1320-1568","authenticated-orcid":false,"given":"Zixian","family":"Yang","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China and University of California, Los Angeles, Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2212-0295","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3638-4042","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7582-5574","authenticated-orcid":false,"given":"Zhaokai","family":"Huang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7686-7688","authenticated-orcid":false,"given":"You","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1269-6620","authenticated-orcid":false,"given":"Jianbin","family":"Lin","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8861-9503","authenticated-orcid":false,"given":"Wenliang","family":"Zhong","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6849-6131","authenticated-orcid":false,"given":"Can","family":"Ye","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arXiv:1607.06450"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1137\/0613015"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Damai Dai Chengqi Deng Chenggang Zhao R. X. Xu Huazuo Gao Deli Chen Jiashi Li Wangding Zeng Xingkai Yu Y. Wu Zhenda Xie Y. K. Li Panpan Huang Fuli Luo Chong Ruan Zhifang Sui and Wenfeng Liang. 2024. DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models. arXiv:2401.06066","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Chuntao Ding Zhichao Lu Shangguang Wang Ran Cheng and Vishnu Naresh Boddeti. 2023. Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives. arXiv:2308.02066 [cs.CV] https:\/\/arxiv.org\/abs\/2308.02066","DOI":"10.1109\/CVPR52729.2023.00749"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5569","author":"Du Nan","year":"2022","unstructured":"Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fedus, Maarten P Bosma, Zongwei Zhou, Tao Wang, Emma Wang, Kellie Webster, Marie Pellat, Kevin Robinson, Kathleen Meier-Hellstern, Toju Duke, Lucas Dixon, Kun Zhang, Quoc Le, Yonghui Wu, Zhifeng Chen, and Claire Cui. 2022. GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162). PMLR, Baltimore, Maryland, USA, 5547-5569."},{"key":"e_1_3_2_1_7_1","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res., Vol. 23, 1, Article 120 (2022), 39 pages.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557624"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). Association for Computing Machinery","author":"Gong Shansan","unstructured":"Shansan Gong and Kenny Q. Zhu. 2022. Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). Association for Computing Machinery, New York, NY, USA, 1185\u20131195."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_1_11_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de las Casas Emma Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2024. Mixtral of Experts. arXiv:2401.04088"},{"key":"e_1_3_2_1_12_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. CoRR, Vol. abs\/1412.6980 (2014), 1-15. arXiv:1412.6980 https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net, Virtual Event, 18 pages. https:\/\/openreview.net\/forum?id=qrwe7XHTmYb","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GS, hard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In International Conference on Learning Representations (ICLR). OpenReview.net, Virtual Event, 18 pages. https:\/\/openreview.net\/forum?id=qrwe7XHTmYb"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Hanxue Liang Zhiwen Fan Rishov Sarkar Ziyu Jiang Tianlong Chen Kai Zou Yu Cheng Cong Hao and Zhangyang Wang. 2022. M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design. arXiv:2210.14793 [cs.CV] https:\/\/arxiv.org\/abs\/2210.14793","DOI":"10.52202\/068431-2062"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). Association for Computing Machinery","author":"Ma Jiaqi","year":"1930","unstructured":"Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H. Chi. 2018. Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD). Association for Computing Machinery, New York, NY, USA, 1930\u20131939."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (PMLR","volume":"533","author":"McMahan Brendan","year":"2011","unstructured":"Brendan McMahan. 2011. Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (PMLR, Vol. 15). PMLR, Fort Lauderdale, FL, USA, 525-533."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608814"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615482"},{"key":"e_1_3_2_1_19_1","volume-title":"6th International Conference on Learning Representations, 2018, Workshop Track Proceedings (ICLR). OpenReview.net","author":"Ramachandran Prajit","year":"2018","unstructured":"Prajit Ramachandran, Barret Zoph, and Quoc V Le. 2018. Searching for activation functions. In 6th International Conference on Learning Representations, 2018, Workshop Track Proceedings (ICLR). OpenReview.net, Vancouver, BC, Canada, 13 pages. https:\/\/openreview.net\/forum?id=Hkuq2EkPf"},{"key":"e_1_3_2_1_20_1","volume-title":"Collaborative Filtering Recommender Systems","author":"Schafer J. Ben","unstructured":"J. Ben Schafer, Dan Frankowski, Jon Herlocker, and Shilad Sen. 2007. Collaborative Filtering Recommender Systems. Springer, Berlin, Heidelberg, 291-324."},{"key":"e_1_3_2_1_21_1","volume-title":"Barret Zoph, William Fedus, Xinyun Chen, Tu Vu, Yuexin Wu, Wuyang Chen, Albert Webson, Yunxuan Li, Vincent Zhao, Hongkun Yu, Kurt Keutzer, Trevor Darrell, and Denny Zhou.","author":"Shen Sheng","year":"2023","unstructured":"Sheng Shen, Le Hou, Yanqi Zhou, Nan Du, Shayne Longpre, Jason Wei, Hyung Won Chung, Barret Zoph, William Fedus, Xinyun Chen, Tu Vu, Yuexin Wu, Wuyang Chen, Albert Webson, Yunxuan Li, Vincent Zhao, Hongkun Yu, Kurt Keutzer, Trevor Darrell, and Denny Zhou. 2023. Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models. arXiv:2305.14705 [cs.CL] https:\/\/arxiv.org\/abs\/2305.14705"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_23_1","first-page":"242","article-title":"Transfer Learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. IGI Global, Hershey","author":"Torrey Lisa","year":"2010","unstructured":"Lisa Torrey and Jude Shavlik. 2010. Transfer Learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. IGI Global, Hershey, PA, USA, 242-264.","journal-title":"PA, USA"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709416"},{"key":"e_1_3_2_1_25_1","volume-title":"Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang.","author":"Wang Yuhao","year":"2023","unstructured":"Yuhao Wang, Ha Tsz Lam, Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang. 2023. Multi-Task Deep Recommender Systems: A Survey. arXiv:2302.03525 [cs.IR] https:\/\/arxiv.org\/abs\/2302.03525"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657686"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_28_1","unstructured":"Jie Zhou Qian Yu Chuan Luo and Jing Zhang. 2023. Feature decomposition for reducing negative transfer: a novel multi-task learning method for recommender system (student abstract). In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'23\/IAAI'23\/EAAI'23). AAAI Press Washington DC USA Article 1986 2 pages."},{"key":"e_1_3_2_1_29_1","unstructured":"Barret Zoph Irwan Bello Sameer Kumar Nan Du Yanping Huang Jeff Dean Noam Shazeer and William Fedus. 2022. ST-MoE: Designing Stable and Transferable Sparse Expert Models. arXiv:2202.08906"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:15:38Z","timestamp":1784135738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":29,"alternative-id":["10.1145\/3805712.3808413","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808413","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}