{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:01:31Z","timestamp":1760598091084,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232021D-25"],"award-info":[{"award-number":["2232021D-25"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,6]]},"DOI":"10.1109\/dsaa53316.2021.9564225","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T22:54:28Z","timestamp":1634770468000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Two-Phase Multi-armed Bandit for Online Recommendation"],"prefix":"10.1109","author":[{"given":"Cairong","family":"Yan","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]},{"given":"Haixia","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]},{"given":"Zijian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]},{"given":"Yanting","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Donghua University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref30","first-page":"1","article-title":"Probabilistic matrix factorization","author":"salakhutdinov","year":"0","journal-title":"Proceedings of the 25th Annual Conference on Neural Information Processing Systems"},{"key":"ref10","article-title":"Weighted linear bandits for nonstationary environments","author":"russac","year":"0","journal-title":"Proceedings of the 33rd Conference on Neural Information Processing Systems"},{"key":"ref11","first-page":"420","article-title":"Carousel personalization in music streaming apps with contextual bandits","author":"benda","year":"0","journal-title":"Proceedings of the 14th ACM Conference on Recommender Systems"},{"key":"ref12","first-page":"1959","article-title":"Dynamic clustering of contextual multiarmed bandits","author":"nguyen","year":"0","journal-title":"Proceedings of ACM International Conference on Information and Knowledge Management"},{"key":"ref13","first-page":"11492","article-title":"Neural Contextual Bandits with UCB based Exploration","author":"zhou","year":"0","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"ref14","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"0","journal-title":"Advances in Neural Information Systems"},{"key":"ref15","first-page":"100","article-title":"Thompson sampling for complex online problems","author":"gopalan","year":"0","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref16","first-page":"1297","article-title":"Efficient Thompson Sampling for online matrix-factorization recommendation","author":"kawale","year":"0","journal-title":"Proceedings of the 28th International Conference on Neural"},{"key":"ref17","first-page":"174","article-title":"Thompson sampling for complex online problems","volume":"32","author":"gopalan","year":"0","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning"},{"key":"ref18","first-page":"612","article-title":"Learning to interact with users: a collaborative-bandit approach","author":"ester","year":"0","journal-title":"Proceedings of the 2018 SIAM International Conference on Data Mining"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172967"},{"key":"ref28","first-page":"757","article-title":"Online clustering of bandits","author":"gentile","year":"0","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240354"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347040"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911548"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref29","first-page":"721","article-title":"Multiarmed bandit problems with dependent arms","author":"pandey","year":"0","journal-title":"Proceedings of the 24th International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.32"},{"key":"ref8","first-page":"174","article-title":"On upper-confidence bound policies for switching bandit problems","author":"garivier","year":"0","journal-title":"Proceedings of International Conference on Algorithmic Learning Theory"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.072"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109866"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645732"},{"key":"ref22","first-page":"4268","article-title":"Adapting to user preference changes in interactive recommendation","author":"hariri","year":"0","journal-title":"Proceedings of the 24th International Conference on Artificial Intelligence"},{"key":"ref21","first-page":"2249","article-title":"An empirical evaluation of thompson sampling","author":"mohan","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2695664.2695748"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505690"},{"key":"ref26","first-page":"1253","article-title":"On context-dependent clustering of bandits","author":"gentile","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref25","first-page":"1152","article-title":"Optimal regret analysis of thompson sampling in stochastic multiarmed bandit problem with multiple plays","author":"komiyama","year":"0","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning"}],"event":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","start":{"date-parts":[[2021,10,6]]},"location":"Porto, Portugal","end":{"date-parts":[[2021,10,9]]}},"container-title":["2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564091\/9564109\/09564225.pdf?arnumber=9564225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:37:31Z","timestamp":1659483451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/dsaa53316.2021.9564225","relation":{},"subject":[],"published":{"date-parts":[[2021,10,6]]}}}