{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:45:41Z","timestamp":1784821541604,"version":"3.55.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62236003"],"award-info":[{"award-number":["62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62192784"],"award-info":[{"award-number":["62192784"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>\n            With the expansion of business scenarios, real recommender systems are facing challenges in dealing with the constantly emerging new tasks in multi-task learning frameworks. In this article, we attempt to improve the generalization ability of multi-task recommendations when dealing with new tasks. A novel two-stage prompt-tuning MTL framework (MPT-Rec) is proposed to address task irrelevance and training efficiency problems in multi-task recommender systems. Specifically, we disentangle the task-specific and task-sharing information in the multi-task pre-training stage and then use task-aware prompts to transfer knowledge from other tasks to the new task effectively. By freezing parameters in the pre-training tasks, MPT-Rec solves the negative impacts that may be brought by the new task and greatly reduces the training costs. Extensive experiments on three real-world datasets show the effectiveness of our proposed multi-task learning framework. MPT-Rec achieves the best performance compared to the SOTA multi-task learning method on three real-world datasets. Besides, it maintains comparable model performance but vastly improves the training efficiency (i.e., with up to 10% parameters in the full-training way) in the new task learning. Our code is publicly available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/BAI-LAB\/MPT-Rec\">https:\/\/github.com\/BAI-LAB\/MPT-Rec<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3736403","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T06:48:36Z","timestamp":1747637316000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Multi-task Prompt Tuning for Recommendation"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9607-3551","authenticated-orcid":false,"given":"Ting","family":"Bai","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1519-3851","authenticated-orcid":false,"given":"Le","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7381-042X","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7821-0030","authenticated-orcid":false,"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7602-7686","authenticated-orcid":false,"given":"Cheng","family":"Hou","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9496-5917","authenticated-orcid":false,"given":"Zhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3734-0266","authenticated-orcid":false,"given":"Chuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.446"},{"key":"e_1_3_2_3_2","unstructured":"Arthur Asuncion and David Newman. 2007. UCI Machine Learning Repository. University of California Irvine School of Information and Computer Sciences. Retrieved from http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.104028"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103525"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512043"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_8_2","unstructured":"Zhixuan Chu Hongyan Hao Xin Ouyang Simeng Wang Yan Wang Yue Shen Jinjie Gu Qing Cui Longfei Li Siqiao Xue et al. 2023. Leveraging large language models for pre-trained recommender systems. arXiv:2308.10837. Retrieved from https:\/\/arxiv.org\/abs\/2308.10837"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_10_2","unstructured":"Michael Crawshaw. 2020. Multi-task learning with deep neural networks: A survey. arXiv:2009.09796. Retrieved from https:\/\/arxiv.org\/abs\/2009.09796"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570640"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"e_1_3_2_14_2","first-page":"1126","volume-title":"International Conference on Machine Learning","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126\u20131135."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635754"},{"key":"e_1_3_2_17_2","first-page":"2790","volume-title":"International Conference on Machine Learning","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_18_2","volume-title":"Rtsne: T-Distributed Stochastic Neighbor Embedding Using a Barnes-Hut Implementation","author":"Krijthe Jesse","year":"2014","unstructured":"Jesse Krijthe. 2014. Rtsne: T-Distributed Stochastic Neighbor Embedding Using a Barnes-Hut Implementation. CRAN: Contributed Packages."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01048"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240365"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00236"},{"key":"e_1_3_2_25_2","unstructured":"Minh-Thang Luong Quoc V. Le Ilya Sutskever Oriol Vinyals and Lukasz Kaiser. 2015. Multi-task sequence to sequence learning. arXiv:1511.06114. Retrieved from https:\/\/arxiv.org\/abs\/arXiv:1511.06114"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474239"},{"key":"e_1_3_2_31_2","unstructured":"Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv:1706.05098. Retrieved from https:\/\/arxiv.org\/abs\/1706.05098"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00556"},{"key":"e_1_3_2_33_2","unstructured":"W Shen. 2021. Deepctr: Easy-to-use modular and extendible package of deep-learning based CTR models (2017). GitHub Repository. Retrieved November 2021 from https:\/\/github. com\/shenweichen\/deepctr"},{"key":"e_1_3_2_34_2","unstructured":"Liangcai Su Junwei Pan Ximei Wang Xi Xiao Shijie Quan Xihua Chen and Jie Jiang. 2023. STEM: Unleashing the power of embeddings for multi-task recommendation. arXiv:2308.13537. Retrieved from https:\/\/arxiv.org\/abs\/2308.13537"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6463-x"},{"key":"e_1_3_2_39_2","unstructured":"Richa Upadhyay Ronald Phlypo Rajkumar Saini and Marcus Liwicki. 2023. Less is more\u2014Towards parsimonious multi-task models using structured sparsity. arXiv:2308.12114. Retrieved from https:\/\/arxiv.org\/abs\/2308.12114"},{"key":"e_1_3_2_40_2","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. Retrieved from https:\/\/arxiv.org\/abs\/2302.03525"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591750"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539439"},{"key":"e_1_3_2_43_2","unstructured":"Zhen Wang Rameswar Panda Leonid Karlinsky Rogerio Feris Huan Sun and Yoon Kim. 2023. Multitask prompt tuning enables parameter-efficient transfer learning. arXiv:2303.02861. Retrieved from https:\/\/arxiv.org\/abs\/2303.02861"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00075"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645359"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28416"},{"key":"e_1_3_2_48_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Wu Sen","year":"2019","unstructured":"Sen Wu, Hongyang R. Zhang, and Christopher R\u00e9. 2019. Understanding and improving information transfer in Multi-Task learning. In International Conference on Learning Representations, 1\u201328."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645546"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"e_1_3_2_51_2","unstructured":"Mingzhu Zhang Ruiping Yin Zhen Yang Yipeng Wang and Kan Li. 2023. Advances and challenges of multi-task learning method in recommender system: A survey. arXiv:2305.13843. Retrieved from https:\/\/arxiv.org\/abs\/2305.13843"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Zijian Zhang Shuchang Liu Jiaao Yu Qingpeng Cai Xiangyu Zhao Chunxu Zhang Ziru Liu Qidong Liu Hongwei Zhao Lantao Hu et al. 2024. M3oE: Multi-domain multi-task mixture-of experts recommendation framework. arXiv:2404.18465. Retrieved from https:\/\/arxiv.org\/abs\/2404.18465","DOI":"10.1145\/3626772.3657686"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401169"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3376453"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T15:36:05Z","timestamp":1752593765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3736403"],"URL":"https:\/\/doi.org\/10.1145\/3736403","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,10]]},"assertion":[{"value":"2024-10-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}