{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T01:11:29Z","timestamp":1774487489956,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,16]],"date-time":"2021-10-16T00:00:00Z","timestamp":1634342400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,16]]},"DOI":"10.1145\/3503181.3503203","type":"proceedings-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T23:13:40Z","timestamp":1646176420000},"page":"132-139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation"],"prefix":"10.1145","author":[{"given":"Yong","family":"Liu","sequence":"first","affiliation":[{"name":"Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University, Singapore"}]},{"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"given":"Yinan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"given":"Lizhen","family":"Cui","sequence":"additional","affiliation":[{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & School of Software, Shandong University, China"}]}],"member":"320","published-online":{"date-parts":[[2022,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Arda Antikacioglu and R Ravi. 2017. Post Processing Recommender Systems for Diversity. In KDD\u201917. Arda Antikacioglu and R Ravi. 2017. Post Processing Recommender Systems for Diversity. In KDD\u201917.","DOI":"10.1145\/3097983.3098173"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jaime Carbonell and Jade Goldstein. 1998. The use of MMR diversity-based reranking for reordering documents and producing summaries. In SIGIR\u201998. Jaime Carbonell and Jade Goldstein. 1998. The use of MMR diversity-based reranking for reordering documents and producing summaries. In SIGIR\u201998.","DOI":"10.1145\/290941.291025"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Haokun Chen Xinyi Dai Han Cai Weinan Zhang Xuejian Wang Ruiming Tang Yuzhou Zhang and Yong Yu. 2019. Large-scale Interactive Recommendation with Tree-structured Policy Gradient. In AAAI\u201919. Haokun Chen Xinyi Dai Han Cai Weinan Zhang Xuejian Wang Ruiming Tang Yuzhou Zhang and Yong Yu. 2019. Large-scale Interactive Recommendation with Tree-structured Policy Gradient. In AAAI\u201919.","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_1_4_1","unstructured":"Laming Chen Guoxin Zhang and Eric Zhou. 2018. Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity. In NIPS\u201918. Laming Chen Guoxin Zhang and Eric Zhou. 2018. Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity. In NIPS\u201918."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Peizhe Cheng Shuaiqiang Wang Jun Ma Jiankai Sun and Hui Xiong. 2017. Learning to recommend accurate and diverse items. In WWW\u201917. Peizhe Cheng Shuaiqiang Wang Jun Ma Jiankai Sun and Hui Xiong. 2017. Learning to recommend accurate and diverse items. In WWW\u201917.","DOI":"10.1145\/3038912.3052585"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Qinxu Ding Yong Liu Chunyan Miao Fei Cheng and Haihong Tang. 2021. A Hybrid Bandit Framework for Diversified Recommendation. In AAAI\u201921 Vol.\u00a035. 4036\u20134044. Qinxu Ding Yong Liu Chunyan Miao Fei Cheng and Haihong Tang. 2021. A Hybrid Bandit Framework for Diversified Recommendation. In AAAI\u201921 Vol.\u00a035. 4036\u20134044.","DOI":"10.1609\/aaai.v35i5.16524"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Peng Han Zhongxiao Li Yong Liu Peilin Zhao Jing Li Hao Wang and Shuo Shang. 2020. Contextualized Point-of-Interest Recommendation. In IJCAI\u201920. 2484\u20132490. Peng Han Zhongxiao Li Yong Liu Peilin Zhao Jing Li Hao Wang and Shuo Shang. 2020. Contextualized Point-of-Interest Recommendation. In IJCAI\u201920. 2484\u20132490.","DOI":"10.24963\/ijcai.2020\/344"},{"key":"e_1_3_2_1_8_1","unstructured":"Christopher\u00a0C Johnson. 2014. Logistic matrix factorization for implicit feedback data. NIPS\u201914 27(2014). Christopher\u00a0C Johnson. 2014. Logistic matrix factorization for implicit feedback data. NIPS\u201914 27(2014)."},{"key":"e_1_3_2_1_9_1","unstructured":"Jaya Kawale Hung\u00a0H Bui Branislav Kveton Long Tran-Thanh and Sanjay Chawla. 2015. Efficient Thompson Sampling for Online Matrix Factorization Recommendation. In NIPS\u201915. Jaya Kawale Hung\u00a0H Bui Branislav Kveton Long Tran-Thanh and Sanjay Chawla. 2015. Efficient Thompson Sampling for Online Matrix Factorization Recommendation. In NIPS\u201915."},{"key":"e_1_3_2_1_10_1","unstructured":"Alex Kulesza and Ben Taskar. 2011. k-DPPs: Fixed-size determinantal point processes. In ICML\u201911. Alex Kulesza and Ben Taskar. 2011. k-DPPs: Fixed-size determinantal point processes. In ICML\u201911."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Alex Kulesza Ben Taskar 2012. Determinantal point processes for machine learning. Foundations and Trends\u00ae in Machine Learning 5 2\u20133(2012). Alex Kulesza Ben Taskar 2012. Determinantal point processes for machine learning. Foundations and Trends\u00ae in Machine Learning 5 2\u20133(2012).","DOI":"10.1561\/2200000044"},{"key":"e_1_3_2_1_12_1","volume-title":"Diversity in recommender systems\u2013A survey. Knowledge-Based Systems 123","author":"Kunaver Matev\u017e","year":"2017","unstructured":"Matev\u017e Kunaver and Toma\u017e Po\u017erl . 2017. Diversity in recommender systems\u2013A survey. Knowledge-Based Systems 123 ( 2017 ). Matev\u017e Kunaver and Toma\u017e Po\u017erl. 2017. Diversity in recommender systems\u2013A survey. Knowledge-Based Systems 123 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Neal Lathia Stephen Hailes Licia Capra and Xavier Amatriain. 2010. Temporal diversity in recommender systems. In SIGIR\u201910. Neal Lathia Stephen Hailes Licia Capra and Xavier Amatriain. 2010. Temporal diversity in recommender systems. In SIGIR\u201910.","DOI":"10.1145\/1835449.1835486"},{"key":"e_1_3_2_1_14_1","volume-title":"SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. In KDD\u201921. 3161\u20133171.","author":"Lei Chenyi","year":"2021","unstructured":"Chenyi Lei , Yong Liu , Lingzi Zhang , Guoxin Wang , Haihong Tang , Houqiang Li , and Chunyan Miao . 2021 . SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. In KDD\u201921. 3161\u20133171. Chenyi Lei, Yong Liu, Lingzi Zhang, Guoxin Wang, Haihong Tang, Houqiang Li, and Chunyan Miao. 2021. SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. In KDD\u201921. 3161\u20133171."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Lihong Li Wei Chu John Langford and Robert\u00a0E Schapire. 2010. A contextual-bandit approach to personalized news article recommendation. In WWW\u201910. Lihong Li Wei Chu John Langford and Robert\u00a0E Schapire. 2010. A contextual-bandit approach to personalized news article recommendation. In WWW\u201910.","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_16_1","unstructured":"Timothy\u00a0P Lillicrap Jonathan\u00a0J Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971(2015). Timothy\u00a0P Lillicrap Jonathan\u00a0J Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971(2015)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107085"},{"key":"e_1_3_2_1_18_1","unstructured":"Yuanguo Lin Yong Liu Fan Lin Pengcheng Wu Wenhua Zeng and Chunyan Miao. 2021. A Survey on Reinforcement Learning for Recommender Systems. arXiv preprint arXiv:2109.10665(2021). Yuanguo Lin Yong Liu Fan Lin Pengcheng Wu Wenhua Zeng and Chunyan Miao. 2021. A Survey on Reinforcement Learning for Recommender Systems. arXiv preprint arXiv:2109.10665(2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yong Liu Yingtai Xiao Qiong Wu Chunyan Miao Juyong Zhang Binqiang Zhao and Haihong Tang. 2020. Diversified interactive recommendation with implicit feedback. In AAAI\u201920 Vol.\u00a034. 4932\u20134939. Yong Liu Yingtai Xiao Qiong Wu Chunyan Miao Juyong Zhang Binqiang Zhao and Haihong Tang. 2020. Diversified interactive recommendation with implicit feedback. In AAAI\u201920 Vol.\u00a034. 4932\u20134939.","DOI":"10.1609\/aaai.v34i04.5931"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Shameem\u00a0A Puthiya\u00a0Parambath Nicolas Usunier and Yves Grandvalet. 2016. A coverage-based approach to recommendation diversity on similarity graph. In RecSys\u201916. Shameem\u00a0A Puthiya\u00a0Parambath Nicolas Usunier and Yves Grandvalet. 2016. A coverage-based approach to recommendation diversity on similarity graph. In RecSys\u201916.","DOI":"10.1145\/2959100.2959149"},{"key":"e_1_3_2_1_21_1","unstructured":"Lijing Qin Shouyuan Chen and Xiaoyan Zhu. 2014. Contextual combinatorial bandit and its application on diversified online recommendation. In SDM\u201914. Lijing Qin Shouyuan Chen and Xiaoyan Zhu. 2014. Contextual combinatorial bandit and its application on diversified online recommendation. In SDM\u201914."},{"key":"e_1_3_2_1_22_1","unstructured":"Lijing Qin and Xiaoyan Zhu. 2013. Promoting Diversity in Recommendation by Entropy Regularizer. In IJCAI\u201913. Lijing Qin and Xiaoyan Zhu. 2013. Promoting Diversity in Recommendation by Entropy Regularizer. In IJCAI\u201913."},{"key":"e_1_3_2_1_23_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. In UAI\u201909.","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle , Christoph Freudenthaler , Zeno Gantner , and Lars Schmidt-Thieme . 2009 . BPR: Bayesian personalized ranking from implicit feedback. In UAI\u201909. Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI\u201909."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556270"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Harald Steck Roelof van Zwol and Chris Johnson. 2015. Interactive recommender systems: Tutorial. In RecSys\u201915. ACM. Harald Steck Roelof van Zwol and Chris Johnson. 2015. Interactive recommender systems: Tutorial. In RecSys\u201915. ACM.","DOI":"10.1145\/2792838.2792840"},{"key":"e_1_3_2_1_26_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton S","unstructured":"Richard\u00a0 S Sutton and Andrew\u00a0 G Barto . 2018. Reinforcement learning: An introduction . MIT press . Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM\u201918. ACM. Jiaxi Tang and Ke Wang. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In WSDM\u201918. ACM.","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Huazheng Wang Qingyun Wu and Hongning Wang. 2017. Factorization Bandits for Interactive Recommendation. In AAAI\u201917. Huazheng Wang Qingyun Wu and Hongning Wang. 2017. Factorization Bandits for Interactive Recommendation. In AAAI\u201917.","DOI":"10.1609\/aaai.v31i1.10936"},{"key":"e_1_3_2_1_29_1","unstructured":"Qiong Wu Yong Liu Chunyan Miao Yin Zhao Lu Guan and Haihong Tang. 2019. Recent advances in diversified recommendation. arXiv preprint arXiv:1905.06589(2019). Qiong Wu Yong Liu Chunyan Miao Yin Zhao Lu Guan and Haihong Tang. 2019. Recent advances in diversified recommendation. arXiv preprint arXiv:1905.06589(2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Mi Zhang and Neil Hurley. 2008. Avoiding monotony: improving the diversity of recommendation lists. In RecSys\u201908. Mi Zhang and Neil Hurley. 2008. Avoiding monotony: improving the diversity of recommendation lists. In RecSys\u201908.","DOI":"10.1145\/1454008.1454030"},{"key":"e_1_3_2_1_31_1","volume-title":"Deep learning based recommender system: A survey and new perspectives. Comput. Surveys","author":"Zhang Shuai","year":"2018","unstructured":"Shuai Zhang , Lina Yao , and Aixin Sun . 2018. Deep learning based recommender system: A survey and new perspectives. Comput. Surveys ( 2018 ). Shuai Zhang, Lina Yao, and Aixin Sun. 2018. Deep learning based recommender system: A survey and new perspectives. Comput. Surveys (2018)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Gang Zhao Mong\u00a0Li Lee Wynne Hsu and Wei Chen. 2012. Increasing temporal diversity with purchase intervals. In SIGIR\u201912. Gang Zhao Mong\u00a0Li Lee Wynne Hsu and Wei Chen. 2012. Increasing temporal diversity with purchase intervals. In SIGIR\u201912.","DOI":"10.1145\/2348283.2348309"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Long Xia Liang Zhang Zhuoye Ding Dawei Yin and Jiliang Tang. 2018. Deep Reinforcement Learning for Page-wise Recommendations. In RecSys\u201918. Xiangyu Zhao Long Xia Liang Zhang Zhuoye Ding Dawei Yin and Jiliang Tang. 2018. Deep Reinforcement Learning for Page-wise Recommendations. In RecSys\u201918.","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In KDD\u201918. Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In KDD\u201918.","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"}],"event":{"name":"ICCSE '21: 5th International Conference on Crowd Science and Engineering","location":"Jinan China","acronym":"ICCSE '21"},"container-title":["5th International Conference on Crowd Science and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503181.3503203","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503181.3503203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:49Z","timestamp":1750186849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503181.3503203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,16]]},"references-count":35,"alternative-id":["10.1145\/3503181.3503203","10.1145\/3503181"],"URL":"https:\/\/doi.org\/10.1145\/3503181.3503203","relation":{},"subject":[],"published":{"date-parts":[[2021,10,16]]},"assertion":[{"value":"2022-03-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}