{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:31:28Z","timestamp":1740123088494,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T00:00:00Z","timestamp":1625788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T00:00:00Z","timestamp":1625788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["NRF-NRFF2016-07"],"award-info":[{"award-number":["NRF-NRFF2016-07"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s10994-021-06028-0","type":"journal-article","created":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T16:33:51Z","timestamp":1625848431000},"page":"2085-2105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Variational learning from implicit bandit feedback"],"prefix":"10.1007","volume":"110","author":[{"given":"Quoc-Tuan","family":"Truong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-8677","authenticated-orcid":false,"given":"Hady W.","family":"Lauw","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,9]]},"reference":[{"key":"6028_CR1","unstructured":"Alemi, A., Poole, B., Fischer, I., Dillon, J., Saurous, R. A., & Murphy, K. (2018). Fixing a broken elbo. In ICML, pages 159\u2013168. PMLR."},{"key":"6028_CR2","doi-asserted-by":"crossref","unstructured":"Beel, J., Genzmehr, M., Langer, S., N\u00fcrnberger, A., & Gipp, B. (2013). A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation. In Proceedings of the international workshop on reproducibility and replication in recommender systems evaluation.","DOI":"10.1145\/2532508.2532511"},{"key":"6028_CR3","unstructured":"Blei, D., & Lafferty, J. (2006). Correlated topic models. In\u00a0Advances in neural information processing systems (Vol. 18, p. 147)."},{"issue":"518","key":"6028_CR4","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","volume":"112","author":"DM Blei","year":"2017","unstructured":"Blei, D. M., Kucukelbir, A., & McAuliffe, J. D. (2017). Variational inference: A review for statisticians. Journal of the American Statistical Association, 112(518), 859\u2013877.","journal-title":"Journal of the American Statistical Association"},{"key":"6028_CR5","unstructured":"Botev, A., Zheng, B., & Barber, D. (2017). Complementary sum sampling for likelihood approximation in large scale classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, volume\u00a054. PMLR (Proceedings of Machine Learning Research)."},{"issue":"1","key":"6028_CR6","first-page":"3207","volume":"14","author":"L Bottou","year":"2013","unstructured":"Bottou, L., Peters, J., Qui\u00f1onero-Candela, J., Charles, D. X., Chickering, D. M., Portugaly, E., et al. (2013). Counterfactual reasoning and learning systems: The example of computational advertising. The Journal of Machine Learning Research, 14(1), 3207\u20133260.","journal-title":"The Journal of Machine Learning Research"},{"key":"6028_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Grangier, D., & Auli, M. (2016). Strategies for training large vocabulary neural language models. In ACL.","DOI":"10.18653\/v1\/P16-1186"},{"key":"6028_CR8","doi-asserted-by":"crossref","unstructured":"Garcin, F., Faltings, B., Donatsch, O., Alazzawi, A., Bruttin, C., & Huber, A. (2014). Offline and online evaluation of news recommender systems at swissinfo. ch. In ACM conference on recommender systems.","DOI":"10.1145\/2645710.2645745"},{"key":"6028_CR9","doi-asserted-by":"crossref","unstructured":"Guo, H., Tang, R., Ye, Y., Li, Z., He, X. (2017). Deepfm: a factorization-machine based neural network for ctr prediction. In IJCAI.","DOI":"10.24963\/ijcai.2017\/239"},{"issue":"2","key":"6028_CR10","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/s10618-015-0417-y","volume":"30","author":"B Hidasi","year":"2016","unstructured":"Hidasi, B., & Tikk, D. (2016). General factorization framework for context-aware recommendations. Data Mining and Knowledge Discovery, 30(2), 342\u2013371.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"6028_CR11","unstructured":"Hidasi, B., Karatzoglou, A., Baltrunas, L., & Tikk, D. (2016). Session-based recommendations with recurrent neural networks. In ICLR."},{"key":"6028_CR12","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A. (2016). beta-vae: Learning basic visual concepts with a constrained variational framework."},{"key":"6028_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., Koren, Y., and Volinsky, C. (2008). Collaborative filtering for implicit feedback datasets. In ICDM, pages 263\u2013272. IEEE.","DOI":"10.1109\/ICDM.2008.22"},{"key":"6028_CR14","unstructured":"Ie, E., Hsu, C.-W., Mladenov, M., Jain, V., Narvekar, S., Wang, J., Wu, R., Boutilier, C. (2019). Recsim: A configurable simulation platform for recommender systems. arXiv preprint arXiv:1909.04847."},{"key":"6028_CR15","unstructured":"Jeunen, O., Mykhaylov, D., Rohde, D., Vasile, F., Gilotte, A., & Bompaire, M. (2019). Learning from bandit feedback: An overview of the state-of-the-art."},{"key":"6028_CR16","unstructured":"Joachims, T., Swaminathan, A., & de\u00a0Rijke, M. (2018). Deep learning with logged bandit feedback. In International Conference on Representation Learning."},{"issue":"2","key":"6028_CR17","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1023\/A:1007665907178","volume":"37","author":"MI Jordan","year":"1999","unstructured":"Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999). An introduction to variational methods for graphical models. Machine learning, 37(2), 183\u2013233.","journal-title":"Machine learning"},{"key":"6028_CR18","unstructured":"Kawale, J., Bui, H. H., Kveton, B., Tran-Thanh, L., & Chawla, S. (2015). Efficient thompson sampling for online matrix-factorization recommendation. In Advances in neural information processing systems (pp. 1297\u20131305)."},{"key":"6028_CR19","unstructured":"Kingma, D.P., & Welling, M. (2014). Auto-encoding variational bayes. In International Conference on Learning Representations."},{"issue":"8","key":"6028_CR20","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2009.263","volume":"42","author":"Y Koren","year":"2009","unstructured":"Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30\u201337.","journal-title":"Computer"},{"key":"6028_CR21","unstructured":"Krause, A., & Ong, C. S. (2011, January). Contextual Gaussian Process Bandit Optimization. In Advances in neural information processing systems (pp. 2447\u20132455)."},{"key":"6028_CR22","unstructured":"Langford, J., & Zhang, T. (2007). The epoch-greedy algorithm for contextual multi-armed bandits. In Advances in neural information processing systems (Vol. 20, pp. 96\u20131)."},{"key":"6028_CR23","doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., & Schapire, R.E. (2010). A contextual-bandit approach to personalized news article recommendation. In International World Wide Web Conference.","DOI":"10.1145\/1772690.1772758"},{"key":"6028_CR24","doi-asserted-by":"crossref","unstructured":"Lian, J., Zhou, X., Zhang, F., Chen, Z., Xie, X., & Sun, G. (2018). xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1754\u20131763.","DOI":"10.1145\/3219819.3220023"},{"key":"6028_CR25","doi-asserted-by":"crossref","unstructured":"Liang, D., Krishnan, R.G., Hoffman, M.\u00a0D., & Jebara, T. (2018). Variational autoencoders for collaborative filtering. In WWW.","DOI":"10.1145\/3178876.3186150"},{"key":"6028_CR26","unstructured":"Miao, Y., Yu, L., & Blunsom, P. (2016). Neural variational inference for text processing. In ICML."},{"key":"6028_CR27","unstructured":"Morin, F., & Bengio, Y. (2005). Hierarchical probabilistic neural network language model. In AISTATS."},{"key":"6028_CR28","unstructured":"Rendle, S., Freudenthaler, C., Gantner, Z., & Schmidt-Thieme, L. (2009). Bpr: Bayesian personalized ranking from implicit feedback. In UAI."},{"key":"6028_CR29","unstructured":"Rezende, D.\u00a0J., Mohamed, S., and Wierstra, D. (2014). Stochastic backpropagation and approximate inference in deep generative models. In ICML."},{"key":"6028_CR30","doi-asserted-by":"crossref","unstructured":"Richardson, M., Dominowska, E., & Ragno, R. (2007). Predicting clicks: estimating the click-through rate for new ads. In WWW.","DOI":"10.1145\/1242572.1242643"},{"key":"6028_CR31","unstructured":"Rohde, D., Bonner, S., Dunlop, T., Vasile, F., & Karatzoglou, A. (2018). Recogym: A reinforcement learning environment for the problem of product recommendation in online advertising. arXiv preprint arXiv:1808.00720."},{"key":"6028_CR32","doi-asserted-by":"crossref","unstructured":"Rossetti, M., Stella, F., & Zanker, M. (2016). Contrasting offline and online results when evaluating recommendation algorithms. In ACM Conference on Recommender Systems.","DOI":"10.1145\/2959100.2959176"},{"issue":"2","key":"6028_CR33","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0378-3758(00)00115-4","volume":"90","author":"H Shimodaira","year":"2000","unstructured":"Shimodaira, H. (2000). Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2), 227\u2013244.","journal-title":"Journal of Statistical Planning and Inference"},{"key":"6028_CR34","doi-asserted-by":"crossref","unstructured":"Sun, W., Khenissi, S., Nasraoui, O., & Shafto, P. (2019). Debiasing the human-recommender system feedback loop in collaborative filtering. In Companion Proceedings of The 2019 World Wide Web Conference, pages 645\u2013651.","DOI":"10.1145\/3308560.3317303"},{"key":"6028_CR35","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Introduction to reinforcement learning (Vol. 135). Cambridge: MIT Press."},{"issue":"1","key":"6028_CR36","first-page":"1731","volume":"16","author":"A Swaminathan","year":"2015","unstructured":"Swaminathan, A., & Joachims, T. (2015a). Batch learning from logged bandit feedback through counterfactual risk minimization. Journal of Machine Learning Research, 16(1), 1731\u20131755.","journal-title":"Journal of Machine Learning Research"},{"key":"6028_CR37","doi-asserted-by":"crossref","unstructured":"Swaminathan, A. & Joachims, T (2015b). Counterfactual risk minimization: Learning from logged bandit feedback. In ICML.","DOI":"10.1145\/2740908.2742564"},{"key":"6028_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, G., \u00a0Zhu, X., Song, C., Fan, Y., \u00a0Zhu, H., Ma, X., Yan, Y., Jin, J., Li, H. & Gai, K. (2018). Deep interest network for click-through rate prediction. In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.","DOI":"10.1145\/3219819.3219823"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06028-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06028-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06028-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:07:54Z","timestamp":1657325274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06028-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,9]]},"references-count":38,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["6028"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06028-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2021,7,9]]},"assertion":[{"value":"30 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}