{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T08:57:02Z","timestamp":1780995422501,"version":"3.54.1"},"reference-count":31,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In the real world, the interaction behaviors of users are not isolated. Instead, they occur continuously in a sequential manner. In the absence of project information, it is difficult for ordinary recommendation methods to predict their next interaction behavior, while sequential recommendation can capture the dynamic behavior of users to complete the recommendation task. Existing sequential recommendation methods generally capture more information about interactive sequences by adding auxiliary tasks for strengthening sequence representations. Despite their achievements, they are deficient in mining user\u2010user or item\u2010item multi\u2010level sequence information, and are not efficient in solving multi\u2010task optimization problems. To address the above issues, we propose gradient segmentation\u2010based multi\u2010task sequential recommendation (GS\u2010MTLSR). First, we cluster user interaction sequences, and then maximize the consistency between user sequence features and their corresponding behavior category features through contrastive learning. Second, we construct dynamic global graphs to capture global contextual information and enhance interaction item relationship information of the sequence through graph contrastive learning. For the optimization problem of multiple contrastive learning tasks, this paper adopts the gradient segmentation method to solve gradient conflicts to eliminate the negative cosine similarity between task optimization gradients. In this way, multiple contrastive learning tasks can be leveraged to the sequential recommendation (SR) model. Experimental results show that the recommendation accuracy of the GS\u2010MTLSR model achieves state\u2010of\u2010the\u2010art performance compared to other baseline models.<\/jats:p>","DOI":"10.1002\/cpe.70759","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:29:33Z","timestamp":1780054173000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi\u2010Task Sequential Recommendation Based on Gradient Segmentation"],"prefix":"10.1002","volume":"38","author":[{"given":"Gang","family":"Tian","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering Shandong University of Science and Technology  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering Shandong University of Science and Technology  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Energy and Mining Engineering Shandong University of Science and Technology  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"crossref","unstructured":"S.Wang L.Hu Y.Wang L.Cao Q. Z.Sheng andM.Orgun \u201cSequential Recommender Systems: Challenges Progress and Prospects \u201d arXiv preprint arXiv:2001.04830 (2019).","DOI":"10.24963\/ijcai.2019\/883"},{"key":"e_1_2_12_3_1","doi-asserted-by":"crossref","unstructured":"C.Lei Y.Liu L.Zhang et al. \u201cSemi: A Sequential Multi\u2010Modal Information Transfer Network for e\u2010Commerce Micro\u2010Video Recommendations \u201d inProceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 3161\u20133171 (2021).","DOI":"10.1145\/3447548.3467189"},{"key":"e_1_2_12_4_1","unstructured":"B.Hidasi A.Karatzoglou L.Baltrunas andD.Tikk \u201cSession\u2010Based Recommendations With Recurrent Neural Networks \u201d arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_2_12_5_1","doi-asserted-by":"crossref","unstructured":"Z.Lin M.Li Z.Zheng Y.Cheng andC.Yuan \u201cSelf\u2010Attention Convlstm for Spatiotemporal Prediction \u201d inProceedings of the AAAI Conference on Artificial Intelligence volume 34 11531\u201311538 (2020).","DOI":"10.1609\/aaai.v34i07.6819"},{"key":"e_1_2_12_6_1","doi-asserted-by":"crossref","unstructured":"Y.Chen Z.Liu J.Li J.McAuley andC.Xiong \u201cIntent Contrastive Learning for Sequential Recommendation \u201d inProceedings of the ACM Web Conference 2022 2172\u20132182 (2022).","DOI":"10.1145\/3485447.3512090"},{"key":"e_1_2_12_7_1","doi-asserted-by":"crossref","unstructured":"Z.Fan Z.Liu J.Zhang Y.Xiong L.Zheng andP. S.Yu \u201cContinuous\u2010Time Sequential Recommendation With Temporal Graph Collaborative Transformer \u201d inProceedings of the 30th ACM International Conference on Information & Knowledge Management 433\u2013442 (2021).","DOI":"10.1145\/3459637.3482242"},{"key":"e_1_2_12_8_1","doi-asserted-by":"crossref","unstructured":"R.Cai J.Wu A.San C.Wang andH.Wang \u201cCategory\u2010Aware Collaborative Sequential Recommendation \u201d inProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 388\u2013397 (2021).","DOI":"10.1145\/3404835.3462832"},{"key":"e_1_2_12_9_1","doi-asserted-by":"crossref","unstructured":"J.TangandK.Wang \u201cPersonalized Top\u2010n Sequential Recommendation via Convolutional Sequence Embedding \u201d inProceedings of the Eleventh ACM International Conference on Web Search and Data Mining 565\u2013573 (2018).","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_2_12_10_1","doi-asserted-by":"crossref","unstructured":"W.KangandJ.McAuley \u201cSelf\u2010Attentive Sequential Recommendation \u201d in2018 IEEE International Conference on Data Mining (ICDM) 197\u2013206. (IEEE 2018).","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_2_12_11_1","doi-asserted-by":"crossref","unstructured":"F.Sun J.Liu J.Wu et al. \u201cBERT4Rec: Sequential Recommendation With Bidirectional Encoder Representations From Transformer \u201d inProceedings of the 28th ACM International Conference on Information and Knowledge Management 1441\u20131450 (2019).","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"e_1_2_12_13_1","doi-asserted-by":"crossref","unstructured":"Y.Wei X.Wang Q.Li et al. \u201cContrastive Learning for Cold\u2010Start Recommendation \u201d inProceedings of the 29th ACM International Conference on Multimedia 5382\u20135390 2021.","DOI":"10.1145\/3474085.3475665"},{"key":"e_1_2_12_14_1","doi-asserted-by":"crossref","unstructured":"K.Zhou H.Wang W. X.Zhao et al. \u201cS3\u2010Rec: Self\u2010Supervised Learning for Sequential Recommendation With Mutual Information Maximization \u201d inProceedings of the 29th ACM International Conference on Information & Knowledge Management 1893\u20131902 (2020).","DOI":"10.1145\/3340531.3411954"},{"key":"e_1_2_12_15_1","doi-asserted-by":"crossref","unstructured":"J.Wu X.Wang F.Feng et al. \u201cSelf\u2010Supervised Graph Learning for Recommendation \u201d inProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 726\u2013735 (2021).","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_2_12_16_1","unstructured":"Z.Liu Y.Chen J.Li P. S.Yu J.McAuley andC.Xiong \u201cContrastive Self\u2010Supervised Sequential Recommendation with Robust Augmentation \u201d arXiv preprint arXiv:2108.06479 (2021)."},{"key":"e_1_2_12_17_1","doi-asserted-by":"crossref","unstructured":"J.Li Y.Wang andJ.McAuley \u201cTime Interval Aware Self\u2010Attention for Sequential Recommendation \u201d inProceedings of the 13th International Conference on Web Search and Data Mining 322\u2013330 (2020).","DOI":"10.1145\/3336191.3371786"},{"key":"e_1_2_12_18_1","unstructured":"Z.Liu L.Meng F.Jiang J.Zhang andP. S.Yu \u201cDeoscillated Graph Collaborative Filtering \u201d arXiv preprint arXiv:2011.02100 (2020)."},{"key":"e_1_2_12_19_1","doi-asserted-by":"crossref","unstructured":"J.Ma C.Zhou H.Yang P.Cui X.Wang andW.Zhu \u201cDisentangled Self\u2010Supervision in Sequential Recommenders \u201d inProceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 483\u2013491 (2020).","DOI":"10.1145\/3394486.3403091"},{"key":"e_1_2_12_20_1","unstructured":"X.Xie F.Sun Z.Liu et al. \u201cContrastive Learning for Sequential Recommendation \u201d arXiv preprint arXiv:2010.14395 (2020)."},{"key":"e_1_2_12_21_1","unstructured":"Y.Zhang Y.Liu Y.Xu et al. \u201cEnhancing Sequential Recommendation with Graph Contrastive Learning \u201d arXiv preprint arXiv:2205.14837 (2022)."},{"key":"e_1_2_12_22_1","first-page":"5824","article-title":"Gradient Surgery for Multi\u2010Task Learning","volume":"33","author":"Yu T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_23_1","doi-asserted-by":"crossref","unstructured":"R.HeandJ.McAuley \u201cUps and Downs: Modeling the Visual Evolution of Fashion Trends With One\u2010Class Collaborative Filtering \u201d inProceedings of the 25th International Conference on World Wide Web 507\u2013517 (2016).","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_2_12_24_1","unstructured":"P.Kingma DiederikandJ. B.Adam \u201cA Method for Stochastic Optimization \u201d arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_12_25_1","doi-asserted-by":"crossref","unstructured":"X.He K.Deng X.Wang Y.Li Y.Zhang andM.Wang \u201cLightgcn: Simplifying and Powering Graph Convolution Network for Recommendation \u201d inProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval 639\u2013648 (2020).","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_2_12_26_1","first-page":"1024","article-title":"Inductive Representation Learning on Large Graphs","volume":"30","author":"Hamilton W.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_2_12_27_1","first-page":"857","article-title":"Self\u2010Supervised Learning: Generative or Contrastive","volume":"35","author":"Liu X.","year":"2021","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_12_28_1","unstructured":"K.HassaniandA. H.Khasahmadi \u201cContrastive Multi\u2010View Representation Learning on Graphs \u201d inInternational Conference on Machine Learning 4116\u20134126. (PMLR 2020)."},{"key":"e_1_2_12_29_1","first-page":"43","article-title":"A Review of Research on User Behavior Sequence Personalized Recommendation","volume":"5","author":"Wang Q.","year":"2022","journal-title":"Journal of Chinese Mini\u2010Micro Computer Systems"},{"key":"e_1_2_12_30_1","doi-asserted-by":"crossref","unstructured":"W. C.Kang M.Wan andJ.McAuley \u201cRecommendation Through Mixtures of Heterogeneous Item Relationships \u201d inProceedings of the 27th ACM International Conference on Information and Knowledge Management 1143\u20131152 (2018).","DOI":"10.1145\/3269206.3271792"},{"key":"e_1_2_12_31_1","doi-asserted-by":"crossref","unstructured":"X.Ma L.Zhao G.Huang et al. \u201cEntire Space Multi\u2010Task Model: An Effective Approach for Estimating Post\u2010Click Conversion Rate \u201d inThe 41st International ACM SIGIR Conference on Research & Development in Information Retrieval 1137\u20131140 (2018).","DOI":"10.1145\/3209978.3210104"},{"key":"e_1_2_12_32_1","doi-asserted-by":"crossref","unstructured":"S.Wang L.Hu L.Cao X.Huang D.Lian andW.Liu \u201cAttention\u2010Based Transactional Context Embedding for Next\u2010Item Recommendation \u201d inProceedings of the AAAI Conference on Artificial Intelligence Volume 32 (2018).","DOI":"10.1609\/aaai.v32i1.11851"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70759","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70759","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:56:57Z","timestamp":1780991817000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":31,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1002\/cpe.70759"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70759","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"2026-01-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70759"}}