{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T06:15:11Z","timestamp":1764828911172,"version":"3.41.2"},"reference-count":26,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"vor","delay-in-days":287,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"crossref","award":["2017YFB1002304"],"award-info":[{"award-number":["2017YFB1002304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Training models to predict click and order targets at the same time. For better user satisfaction and business effectiveness, multitask learning is one of the most important methods in e\u2010commerce. Some existing researches model user representation based on historical behaviour sequence to capture user interests. It is often the case that user interests may change from their past routines. However, multi\u2010perspective attention has broad horizon, which covers different characteristics of human reasoning, emotions, perception, attention, and memory. In this paper, we attempt to introduce the multi\u2010perspective attention and sequence behaviour into multitask learning. Our proposed method offers better understanding of user interest and decision. To achieve more flexible parameter sharing and maintaining the special feature advantage of each task, we improve the attention mechanism at the view of expert interactive. To the best of our knowledge, we firstly propose the implicit interaction mode, the explicit hard interaction mode, the explicit soft interaction mode, and the data fusion mode in multitask learning. We do experiments on public data and lab medical data. The results show that our model consistently achieves remarkable improvements to the state\u2010of\u2010the\u2010art method.<\/jats:p>","DOI":"10.1155\/2021\/8550270","type":"journal-article","created":{"date-parts":[[2021,10,16]],"date-time":"2021-10-16T02:27:50Z","timestamp":1634351270000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Multitask Learning Model with Multiperspective Attention and Its Application in Recommendation"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5457-3240","authenticated-orcid":false,"given":"Yingshuai","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0647-3154","authenticated-orcid":false,"given":"Dezheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Aziguli","family":"Wulamu","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,10,15]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6677920"},{"key":"e_1_2_9_2_2","doi-asserted-by":"crossref","unstructured":"MaJ. ZhaoZ. YiX. ChenJ. HongL. andChiE. H. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining August 2018 London UK 1930\u20131939 https:\/\/doi.org\/10.1145\/3219819.3220007 2-s2.0-85051473411.","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"ZhaoZ. HongL. andWeiL. Recommending what video to watch next: a multitask ranking system Proceedings of the 13th ACM Conference on Recommender Systems September 2019 Copenhagen Denmark 43\u201351.","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"WenH. ZhangJ. andWangY. Entire space multi-task modeling via post-click behavior decomposition for conversion rate prediction Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval July 2020 Xi\u2019an China 2377\u20132386.","DOI":"10.1145\/3397271.3401443"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301216"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"QinZ. ChengY. ZhaoZ. ChenZ. MetzlerD. andQinJ. Multitask mixture of sequential experts for user activity streams Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining July 2020 New York NY USA 3083\u20133091 https:\/\/doi.org\/10.1145\/3394486.3403359.","DOI":"10.1145\/3394486.3403359"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"TangH. LiuJ. ZhaoM. andGongX. Progressive layered extraction (PLE): a novel multi-task learning (MTL) model for personalized recommendations Proceedings of the Fourteenth ACM Conference on Recommender Systems September 2020 New York NY USA 269\u2013278 https:\/\/doi.org\/10.1145\/3383313.3412236.","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"WangY. WangX. andBeutelA. Understanding and improving fairness-accuracy trade-offs in multi-task learning 2021 arXiv preprint arXiv:2106.02705.","DOI":"10.1145\/3447548.3467326"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"XiD. ChenZ. andYanP. Modeling the sequential dependence among audience multi-step conversions with multi-task learning in targeted display advertising 2021 arXiv preprint arXiv:2105.08489.","DOI":"10.1145\/3447548.3467071"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"FanX. LiuZ. andLianJ. Lighter and better: low-rank decomposed self-attention networks for next-item recommendation Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval July 2021 Montreal Canada 1733\u20131737.","DOI":"10.1145\/3404835.3462978"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"FeiH. ZhangJ. andZhouX. GemNN: gating-enhanced multi-task neural networks with feature interaction learning for CTR prediction Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval July 2021 Montreal Canada 2166\u20132171.","DOI":"10.1145\/3404835.3463116"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"DingK. DongX. andHeY. MSSM: a multiple-level sparse sharing model for efficient multi-task learning Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval July 2021 Montreal Canada 2237\u20132241.","DOI":"10.1145\/3404835.3463022"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"WenH. ZhangJ. andLvF. Hierarchically modeling micro and macro behaviors via multi-task learning for conversion rate prediction 2021 arXiv preprint arXiv:2104.09713.","DOI":"10.1145\/3404835.3463053"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"ZhaoJ. DuB. SunL. ZhuangF. LvW. andXiongH. Multiple relational attention network for multi-task learning ACM reference format: multiple relational attention network for multi-task learning Proceedings of the Kdd August 2019 Anchorage AK USA 1123\u20131131.","DOI":"10.1145\/3292500.3330861"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"TangF. XiaoC. WangF. ZhouJ. andLehmanL. H. Retaining privileged information for multi-task learning Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining August 2019 Anchorage AK USA 1369\u20131377 https:\/\/doi.org\/10.1145\/3292500.3330907 2-s2.0-85071173909.","DOI":"10.1145\/3292500.3330907"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"WangW.andHuW. Improving relation extraction by multi-task learning Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence July 2020 Qingdao China 152\u2013157 https:\/\/doi.org\/10.1145\/3409501.3409535.","DOI":"10.1145\/3409501.3409535"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"ShaoC.-J. FuH.-M. andChengP.-J. Improving one-class recommendation with multi-tasking on various preference intensities Proceedings of the Fourteenth ACM Conference on Recommender Systems September 2020 New York NY USA 498\u2013502 https:\/\/doi.org\/10.1145\/3383313.3412224.","DOI":"10.1145\/3383313.3412224"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"YaoY. CaoJ. andChenH. Robust task grouping with representative tasks for clustered multi-task learning Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining August 2019 Anchorage AK USA 1408\u20131417 https:\/\/doi.org\/10.1145\/3292500.3330904 2-s2.0-85071150247.","DOI":"10.1145\/3292500.3330904"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"WangH. ZhangF. ZhaoM. LiW. XieX. andGuoM. \u201cMulti-task feature learning for knowledge graph enhanced recommendation Proceedings of the World Wide Web Conference WWW 2019 May 2019 San Francisco CA USA 2000\u20132010 https:\/\/doi.org\/10.1145\/3308558.3313411 2-s2.0-85066912995.","DOI":"10.1145\/3308558.3313411"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"ChenX. ZhangK. ZhouF. TrajcevskiG. ZhongT. andZhangF. Information cascades modeling via deep multi-task learning Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval July 2019 Paris France 885\u2013888 https:\/\/doi.org\/10.1145\/3331184.3331288 2-s2.0-85073788082.","DOI":"10.1145\/3331184.3331288"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2019.2940845"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"LuoX. AliCoCo: alibaba E-commerce cognitive concept net Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data June 2020 Portland OR USA 313\u2013327 https:\/\/doi.org\/10.1145\/3318464.3386132.","DOI":"10.1145\/3318464.3386132"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"HibbiF.-Z. AbdounO. andHaimoudiE. K. Knowledge management in the expert model of the smart tutoring system Proceedings of the 3rd International Conference on Networking Information Systems & Security March 2020 Marrakech Morocco 1\u20134 https:\/\/doi.org\/10.1145\/3386723.3387895.","DOI":"10.1145\/3386723.3387895"},{"key":"e_1_2_9_24_2","article-title":"Artificial neural networks (the multilayer perceptron)\u2014a review of applications in the atmospheric sciences","volume":"31","author":"Gardner M. W.","year":"1998","journal-title":"Atmospheric Environment"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1023\/a:1007379606734"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"MaX. ZhaoL. HuangG. WangZ. HuZ. ZhuX. andGaiK. Entire space multi-task model: an effective approach for estimating post-click conversion rate Proceedings of the SIGIR Conference September 2018 Tianjin China 1137\u20131140.","DOI":"10.1145\/3209978.3210104"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8550270.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8550270.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8550270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:09:01Z","timestamp":1722946141000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8550270"}},"subtitle":[],"editor":[{"given":"Jin","family":"Jing","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8550270"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8550270","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8550270"}}