{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:54:22Z","timestamp":1777614862718,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"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":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539461","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"2050-2058","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction"],"prefix":"10.1145","author":[{"given":"Kailun","family":"Wu","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijie","family":"Bian","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangming","family":"Chan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lejian","family":"Ren","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Guang","family":"Han","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbo","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-003-1038-1"},{"key":"e_1_3_2_2_2_1","volume-title":"International conference on machine learning. PMLR.","author":"Agrawal Shipra","year":"2013","unstructured":"Shipra Agrawal and Navin Goyal. 2013. Thompson sampling for contextual bandits with linear payoffs. In International conference on machine learning. PMLR."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Robin Allesiardo Rapha\u00ebl F\u00e9raud and Djallel Bouneffouf. 2014. A neural networks committee for the contextual bandit problem. In ICONIP. 374--381.","DOI":"10.1007\/978-3-319-12637-1_47"},{"key":"e_1_3_2_2_4_1","volume-title":"The theory and practice of online learning","author":"Anderson Terry","unstructured":"Terry Anderson. 2008. The theory and practice of online learning .Athabasca University Press."},{"key":"e_1_3_2_2_5_1","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research , Vol. 3, Nov (2002), 397--422.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_6_1","series-title":"SIAM journal on computing","volume-title":"The nonstochastic multiarmed bandit problem","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, and Robert E Schapire. 2002. The nonstochastic multiarmed bandit problem. SIAM journal on computing , Vol. 32 (2002)."},{"key":"e_1_3_2_2_7_1","volume-title":"User Modeling and User-Adapted Interaction","volume":"8","author":"Balabanovi\u0107 Marko","year":"1998","unstructured":"Marko Balabanovi\u0107. 1998. Exploring versus exploiting when learning user models for text recommendation. User Modeling and User-Adapted Interaction , Vol. 8, 1 (1998)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Yikun Ban Jingrui He and Curtiss B Cook. 2021. Multi-facet contextual bandits: A neural network perspective. In SIGKDD. 35--45.","DOI":"10.1145\/3447548.3467299"},{"key":"e_1_3_2_2_9_1","volume-title":"et almbox","author":"Bian Weijie","year":"2022","unstructured":"Weijie Bian, Kailun Wu, Lejian Ren, Qi Pi, et almbox. 2022. CAN: Feature Co-Action Network for Click-Through Rate Prediction. In WSDM. 57--65."},{"key":"e_1_3_2_2_10_1","unstructured":"Charles Blundell Julien Cornebise Koray Kavukcuoglu and Daan Wierstra. 2015. Weight uncertainty in neural network. In ICML. PMLR 1613--1622."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34487-9_40"},{"key":"e_1_3_2_2_12_1","volume-title":"et almbox","author":"Chan Zhangming","year":"2020","unstructured":"Zhangming Chan, Yuchi Zhang, et almbox. 2020. Selection and Generation: Learning towards Multi-Product Advertisement Post Generation. In EMNLP ."},{"key":"e_1_3_2_2_13_1","volume-title":"An empirical evaluation of thompson sampling. Advances in neural information processing systems","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_2_14_1","volume-title":"et almbox","author":"Chen Jiawei","year":"2020","unstructured":"Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, et almbox. 2020. Bias and debias in recommender system: A survey and future directions. (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_16_1","unstructured":"Varsha Dani Thomas P Hayes and Sham M Kakade. 2008. Stochastic linear optimization under bandit feedback. (2008)."},{"key":"e_1_3_2_2_17_1","unstructured":"Chao Du Zhifeng Gao Shuo Yuan Lining Gao Ziyan Li Yifan Zeng Xiaoqiang Zhu Jian Xu Kun Gai and Kuang-Chih Lee. 2021. Exploration in Online Advertising Systems with Deep Uncertainty-Aware Learning. In SIGKDD. 2792--2801."},{"key":"e_1_3_2_2_18_1","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML. PMLR 1050--1059."},{"key":"e_1_3_2_2_19_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_2_20_1","volume-title":"Pranay Kumar Myana, Ferenc Huszar, Wenzhe Shi, Alykhan Tejani, Michael Kneier, and Sourav Das.","author":"Guo Dalin","year":"2020","unstructured":"Dalin Guo, Sofia Ira Ktena, Pranay Kumar Myana, Ferenc Huszar, Wenzhe Shi, Alykhan Tejani, Michael Kneier, and Sourav Das. 2020. Deep bayesian bandits: Exploring in online personalized recommendations. In RecSys. 456--461."},{"key":"e_1_3_2_2_21_1","volume-title":"et almbox","author":"Guo Huifeng","year":"2017","unstructured":"Huifeng Guo, Ruiming TANG, Yunming Ye, Zhenguo Li, et almbox. 2017. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI ."},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_23_1","volume-title":"Contextual gaussian process bandit optimization. Advances in neural information processing systems","author":"Krause Andreas","year":"2011","unstructured":"Andreas Krause and Cheng Ong. 2011. Contextual gaussian process bandit optimization. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_2_24_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. NIPS","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. NIPS (2017)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Lihong Li Wei Chu John Langford and Robert E Schapire. 2010. A contextual-bandit approach to personalized news article recommendation. In WWW .","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Lihong Li Wei Chu John Langford and Xuanhui Wang. 2011. Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms.","DOI":"10.1145\/1935826.1935878"},{"key":"e_1_3_2_2_27_1","volume-title":"ICML. PMLR","author":"Li Lihong","year":"2017","unstructured":"Lihong Li, Yu Lu, and Dengyong Zhou. 2017. Provably optimal algorithms for generalized linear contextual bandits. In ICML. PMLR, 2071--2080."},{"key":"e_1_3_2_2_28_1","volume-title":"Explain","author":"Liquin Emily","unstructured":"Emily Liquin and Tania Lombrozo. 2017. Explain, Explore, Exploit: Effects of Explanation on Information Search.. In CogSci ."},{"key":"e_1_3_2_2_29_1","unstructured":"A. Madry A. Makelov L. Schmidt D. Tsipras and A. Vladu. 2017. Towards Deep Learning Models Resistant to Adversarial Attacks. (2017)."},{"key":"e_1_3_2_2_30_1","volume-title":"et almbox","author":"McInerney James","year":"2018","unstructured":"James McInerney, Benjamin Lacker, et almbox. 2018. Explore, exploit, and explain: personalizing explainable recommendations with bandits. In RecSys ."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi Omar Fawzi and Pascal Frossard. 2017. Universal adversarial perturbations. In CVPR. 1765--1773.","DOI":"10.1109\/CVPR.2017.17"},{"key":"e_1_3_2_2_32_1","volume-title":"Machine learning: a probabilistic perspective","author":"Murphy Kevin P","unstructured":"Kevin P Murphy. 2012. Machine learning: a probabilistic perspective .MIT press."},{"key":"e_1_3_2_2_33_1","volume-title":"et almbox","author":"Nguyen-Thanh Nhan","year":"2019","unstructured":"Nhan Nguyen-Thanh, Dana Marinca, Kinda Khawam, David Rohde, Flavian Vasile, et almbox. 2019. Recommendation System-based Upper Confidence Bound for Online Advertising. arXiv preprint arXiv:1909.04190 (2019)."},{"key":"e_1_3_2_2_34_1","volume-title":"et almbox","author":"Pi Qi","year":"2019","unstructured":"Qi Pi, Weijie Bian, Guorui Zhou, Xiaoqiang Zhu, et almbox. 2019. Practice on long sequential user behavior modeling for click-through rate prediction. In SIGKDD ."},{"key":"e_1_3_2_2_35_1","volume-title":"Summer school on machine learning","author":"Rasmussen Carl Edward","unstructured":"Carl Edward Rasmussen. 2003. Gaussian processes in machine learning. In Summer school on machine learning. Springer, 63--71."},{"key":"e_1_3_2_2_36_1","volume-title":"Are accuracy and robustness correlated","author":"Rozsa Andras","unstructured":"Andras Rozsa, Manuel G\u00fcnther, and Terrance E Boult. 2016. Are accuracy and robustness correlated. In ICMLA. IEEE, 227--232."},{"key":"e_1_3_2_2_37_1","first-page":"2503","article-title":"Hidden technical debt in machine learning systems","volume":"28","author":"Sculley David","year":"2015","unstructured":"David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, et almbox. 2015. Hidden technical debt in machine learning systems. NIPS, Vol. 28 (2015), 2503--2511.","journal-title":"NIPS"},{"key":"e_1_3_2_2_38_1","volume-title":"et almbox","author":"Shah Parikshit","year":"2017","unstructured":"Parikshit Shah, Ming Yang, Sachidanand Alle, Adwait Ratnaparkhi, et almbox. 2017. A practical exploration system for search advertising. In SIGKDD. 1625--1631."},{"key":"e_1_3_2_2_39_1","volume-title":"et almbox","author":"Song Yuhai","year":"2021","unstructured":"Yuhai Song, Lu Wang, Haoming Dang, Weiwei Zhou, Jing Guan, Xiwei Zhao, et almbox. 2021. Underestimation Refinement: A General Enhancement Strategy for Exploration in Recommendation Systems. In SIGIR. 1818--1822."},{"key":"e_1_3_2_2_40_1","volume-title":"Annual Conference on Artificial Intelligence .","author":"Tokic Michel","year":"2010","unstructured":"Michel Tokic. 2010. Adaptive $varepsilon$-greedy exploration in reinforcement learning based on value differences. In Annual Conference on Artificial Intelligence ."},{"key":"e_1_3_2_2_41_1","volume-title":"Fabio De Bona, et almbox","author":"Vanchinathan Hastagiri P","year":"2014","unstructured":"Hastagiri P Vanchinathan, Isidor Nikolic, Fabio De Bona, et almbox. 2014. Explore-exploit in top-n recommender systems via gaussian processes. In RecSys. 225--232."},{"key":"e_1_3_2_2_42_1","volume-title":"et almbox","author":"Zeldes Yoel","year":"2017","unstructured":"Yoel Zeldes, Stavros Theodorakis, Efrat Solodnik, et almbox. 2017. Deep density networks and uncertainty in recommender systems. arXiv:1711.02487 (2017)."},{"key":"e_1_3_2_2_43_1","volume-title":"Neural thompson sampling. arXiv preprint arXiv:2010.00827","author":"Zhang Weitong","year":"2020","unstructured":"Weitong Zhang, Dongruo Zhou, Lihong Li, and Quanquan Gu. 2020. Neural thompson sampling. arXiv preprint arXiv:2010.00827 (2020)."},{"key":"e_1_3_2_2_44_1","volume-title":"et almbox","author":"Zhang Yuanxing","year":"2022","unstructured":"Yuanxing Zhang, Langshi Chen, Siran Yang, Man Yuan, Huimin Yi, Jie Zhang, Jiamang Wang, Jianbo Dong, et almbox. 2022. PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems. In ICDE. IEEE."},{"key":"e_1_3_2_2_45_1","unstructured":"Dongruo Zhou Lihong Li and Quanquan Gu. 2020. Neural contextual bandits with ucb-based exploration. In ICML. PMLR 11492--11502."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_2_47_1","volume-title":"et almbox","author":"Zhou Guorui","year":"2018","unstructured":"Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, et almbox. 2018. Deep interest network for click-through rate prediction. In SIGKDD. 1059--1068."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539461","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:03Z","timestamp":1750186983000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":47,"alternative-id":["10.1145\/3534678.3539461","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539461","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}