{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:59:40Z","timestamp":1765357180147,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T00:00:00Z","timestamp":1657843200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T00:00:00Z","timestamp":1657843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977002"],"award-info":[{"award-number":["61977002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the German Federal Ministry of Education and Research","award":["01IS18036A"],"award-info":[{"award-number":["01IS18036A"]}]},{"name":"State Key Laboratory of Software Development Environment of China","award":["SKLSDE-2022ZX-14"],"award-info":[{"award-number":["SKLSDE-2022ZX-14"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s10115-022-01711-7","type":"journal-article","created":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T19:02:32Z","timestamp":1657911752000},"page":"2239-2265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["CDARL: a contrastive discriminator-augmented reinforcement learning framework for sequential recommendations"],"prefix":"10.1007","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6149-9667","authenticated-orcid":false,"given":"Zhuang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yunpu","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Marcel","family":"Hildebrandt","sequence":"additional","affiliation":[]},{"given":"Yuanxin","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Zhang","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,15]]},"reference":[{"key":"1711_CR1","unstructured":"Burda Y, Edwards H, Pathak D, Storkey AJ, Darrell T, Efros AA (2019) Large-scale study of curiosity-driven learning. ICLR (poster). OpenReview.net"},{"key":"1711_CR2","doi-asserted-by":"crossref","unstructured":"Chen M, Beutel A, Covington P, Jain S, Belletti F, Chi EH (2019) Top-k off-policy correction for a REINFORCE recommender system. In: WSDM. ACM, pp 456\u2013464","DOI":"10.1145\/3289600.3290999"},{"key":"1711_CR3","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton GE (2020) A simple framework for contrastive learning of visual representations. In: ICML, vol 119. PMLR, pp 1597\u20131607"},{"key":"1711_CR4","unstructured":"Chen T, Kornblith S, Swersky K, Norouzi M, Hinton GE (2020) Big self-supervised models are strong semi-supervised learners. In: Neurips"},{"key":"1711_CR5","doi-asserted-by":"crossref","unstructured":"Chen T, Wong RC (2020) Handling information loss of graph neural networks for session-based recommendation. In: KDD. ACM, pp 1172\u20131180","DOI":"10.1145\/3394486.3403170"},{"key":"1711_CR6","unstructured":"Chen X, Fan H, Girshick RB, He K (2020) Improved baselines with momentum contrastive learning. CoRR, arXiv:2003.04297"},{"key":"1711_CR7","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1). Association for Computational Linguistics, pp 4171\u20134186"},{"key":"1711_CR8","unstructured":"Glorot X, Bengio Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In: AISTATS, vol 9. JMLR.org, pp 249\u2013256"},{"key":"1711_CR9","unstructured":"Haghgoo B, Zhou A, Sharma A, Finn C (2021) Discriminator augmented model-based reinforcement learning. CoRR, arXiv:2103.12999"},{"key":"1711_CR10","unstructured":"Hassani K, Ahmadi AHK (2020) Contrastive multi-view representation learning on graphs. In: ICML, vol 119. PMLR, pp 4116\u20134126"},{"key":"1711_CR11","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick RB (2020) Momentum contrast for unsupervised visual representation learning. In: CVPR. IEEE, pp 9726\u20139735","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1711_CR12","unstructured":"H\u00e9naff OJ (2020) Data-efficient image recognition with contrastive predictive coding. In: ICML, vol 119. PMLR, pp 4182\u20134192"},{"key":"1711_CR13","doi-asserted-by":"crossref","unstructured":"Hidasi B, Karatzoglou A (2018) Recurrent neural networks with top-k gains for session-based recommendations. In: CIKM. ACM, pp 843\u2013852","DOI":"10.1145\/3269206.3271761"},{"key":"1711_CR14","unstructured":"Hidasi B, Karatzoglou A, Baltrunas L, Tikk D (2016) Session-based recommendations with recurrent neural networks. In: ICLR (poster)"},{"key":"1711_CR15","doi-asserted-by":"crossref","unstructured":"Kang W, McAuley JJ (2018) Self-attentive sequential recommendation. In: ICDM. IEEE Computer Society, pp 197\u2013206","DOI":"10.1109\/ICDM.2018.00035"},{"key":"1711_CR16","unstructured":"Kim H, Kim J, Jeong Y, Levine S, Song HO (2019) EMI: exploration with mutual information. In: ICML, vol 97. PMLR, pp 3360\u20133369"},{"key":"1711_CR17","unstructured":"Kumar NM (2018) Empowerment-driven exploration using mutual information estimation. CoRR, arXiv:1810.05533"},{"key":"1711_CR18","unstructured":"Kurbiel T, Khaleghian S (2017) Training of deep neural networks based on distance measures using rmsprop. arXiv preprint arXiv:1708.01911"},{"key":"1711_CR19","doi-asserted-by":"crossref","unstructured":"Lei Y, Pei H, Yan H, Li W (2020) Reinforcement learning based recommendation with graph convolutional q-network. In: SIGIR. ACM, pp 1757\u20131760","DOI":"10.1145\/3397271.3401237"},{"key":"1711_CR20","doi-asserted-by":"crossref","unstructured":"Li J, Ren P, Chen Z, Ren Z, Lian T, Ma J (2017) Neural attentive session-based recommendation. In: CIKM. ACM, pp 1419\u20131428","DOI":"10.1145\/3132847.3132926"},{"key":"1711_CR21","unstructured":"Li Y, Gu C, Dullien T, Vinyals O, Kohli P (2019) Graph matching networks for learning the similarity of graph structured objects. In: ICML, vol 97. PMLR, pp 3835\u20133845"},{"issue":"5","key":"1711_CR22","first-page":"566","volume":"6","author":"A Lydia","year":"2019","unstructured":"Lydia A, Francis S (2019) Adagrad\u2014an optimizer for stochastic gradient descent. Int J Inf Comput Sci 6(5):566\u2013568","journal-title":"Int J Inf Comput Sci"},{"key":"1711_CR23","doi-asserted-by":"crossref","unstructured":"Ma J, Zhao Z, Yi X, Yang J, Chen M, Tang J, Chi EH (2020) Off-policy learning in two-stage recommender systems. In: WWW. ACM\/IW3C2, pp 463\u2013473","DOI":"10.1145\/3366423.3380130"},{"key":"1711_CR24","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: NIPS, pp 3111\u20133119"},{"key":"1711_CR25","doi-asserted-by":"crossref","unstructured":"Pathak D, Agrawal P, Efros AA, Darrell T (2017) Curiositydriven exploration by self-supervised prediction. In: ICML, vol 70. PMLR, pp 2778\u20132787","DOI":"10.1109\/CVPRW.2017.70"},{"key":"1711_CR26","unstructured":"Sun F, Hoffmann J, Verma V, Tang J (2020) Infograph: unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In: ICLR. OpenReview.net"},{"key":"1711_CR27","doi-asserted-by":"crossref","unstructured":"Tang J, Wang K (2018) Personalized top-n sequential recommendation via convolutional sequence embedding. In: WSDM. ACM, pp 565\u2013573","DOI":"10.1145\/3159652.3159656"},{"key":"1711_CR28","unstructured":"van den Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. CoRR, arXiv:1807.03748"},{"key":"1711_CR29","unstructured":"van Hasselt H (2010) Double q-learning. In: NIPS. Curran Associates, Inc., pp 2613\u20132621"},{"key":"1711_CR30","doi-asserted-by":"crossref","unstructured":"Wang S, Hu L,Wang Y, Cao L, Sheng QZ, Orgun MA (2019) Sequential recommender systems: challenges, progress and prospects. In: IJCAI. ijcai.org, pp 6332\u20136338","DOI":"10.24963\/ijcai.2019\/883"},{"key":"1711_CR31","doi-asserted-by":"crossref","unstructured":"Wang W, Zhang W, Liu S, Liu Q, Zhang B, Lin L, Zha H (2020) Beyond clicks: modeling multi-relational item graph for session-based target behavior prediction. In: WWW. ACM\/IW3C2, pp 3056\u20133062","DOI":"10.1145\/3366423.3380077"},{"key":"1711_CR32","doi-asserted-by":"crossref","unstructured":"Wang Z, Wei W, Cong G, Li X, Mao X, Qiu M (2020) Global context enhanced graph neural networks for session-based recommendation. In: SIGIR. ACM, pp 169\u2013178","DOI":"10.1145\/3397271.3401142"},{"key":"1711_CR33","doi-asserted-by":"crossref","unstructured":"Wu S, Tang Y, Zhu Y,Wang L, Xie X, Tan T (2019) Session-based recommendation with graph neural networks. In: AAAI. AAAI Press, pp 346\u2013353","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"1711_CR34","doi-asserted-by":"crossref","unstructured":"Xian Y, Fu Z, Muthukrishnan S, de Melo G, Zhang Y (2019) Reinforcement knowledge graph reasoning for explainable recommendation. In: SIGIR. ACM, pp 285\u2013294","DOI":"10.1145\/3331184.3331203"},{"key":"1711_CR35","unstructured":"Xie X, Sun F, Liu Z, Gao J, Ding B, Cui B (2020) Contrastive pre-training for sequential recommendation. CoRR, arXiv:2010.14395"},{"key":"1711_CR36","doi-asserted-by":"crossref","unstructured":"Xin X, Karatzoglou A, Arapakis I, Jose JM (2020) Self-supervised reinforcement learning for recommender systems. In: SIGIR. ACM, pp 931\u2013940","DOI":"10.1145\/3397271.3401147"},{"key":"1711_CR37","unstructured":"Yu X, Lyu Y, Tsang IW (2020) Intrinsic reward driven imitation learning via generative model. In: ICML, vol 119. PMLR, pp 10925\u201310935"},{"key":"1711_CR38","doi-asserted-by":"crossref","unstructured":"Yuan F, Karatzoglou A, Arapakis I, Jose JM, He X (2019) A simple convolutional generative network for next item recommendation. In: WSDM. ACM, pp 582\u2013590","DOI":"10.1145\/3289600.3290975"},{"key":"1711_CR39","unstructured":"Zeiler MD (2012) Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701"},{"key":"1711_CR40","doi-asserted-by":"crossref","unstructured":"Zhao X, Zhang L, Ding Z, Xia L, Tang J, Yin D (2018) Recommendations with negative feedback via pairwise deep reinforcement learning. In: KDD. ACM, pp 1040\u20131048","DOI":"10.1145\/3219819.3219886"},{"key":"1711_CR41","doi-asserted-by":"crossref","unstructured":"Zhou C, Ma J, Zhang J, Zhou J, Yang H (2021) Contrastive learning for debiased candidate generation in large-scale recommender systems","DOI":"10.1145\/3447548.3467102"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01711-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-022-01711-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01711-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,6]],"date-time":"2022-08-06T03:23:22Z","timestamp":1659756202000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-022-01711-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,15]]},"references-count":41,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["1711"],"URL":"https:\/\/doi.org\/10.1007\/s10115-022-01711-7","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2022,7,15]]},"assertion":[{"value":"29 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interests regarding the publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"We train all models on a single NVIDIA GeForce GTX 1080 Ti GPU.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}