{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:05:42Z","timestamp":1775073942527,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,1,22]],"date-time":"2020-01-22T00:00:00Z","timestamp":1579651200000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["NST DGE-1829071"],"award-info":[{"award-number":["NST DGE-1829071"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,1,20]]},"DOI":"10.1145\/3336191.3371785","type":"proceedings-article","created":{"date-parts":[[2020,1,22]],"date-time":"2020-01-22T14:08:16Z","timestamp":1579702096000},"page":"313-321","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":101,"title":["Interpretable Click-Through Rate Prediction through Hierarchical Attention"],"prefix":"10.1145","author":[{"given":"Zeyu","family":"Li","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Inc., Princeton, NJ, USA"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Google Inc., Mountain View, CA, USA"}]},{"given":"Haifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Inc., Princeton, NJ, USA"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,1,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate. arXiv e-prints","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. arXiv e-prints , Vol. abs\/1409.0473 (2014)."},{"key":"e_1_3_2_1_2_1","volume-title":"Frappe: Understanding the Usage and Perception of Mobile App Recommendations In-The-Wild. arXiv preprint arXiv:1505.03014","author":"Baltrunas Linas","year":"2015","unstructured":"Linas Baltrunas, Karen Church, Alexandros Karatzoglou, and Nuria Oliver. 2015. Frappe: Understanding the Usage and Perception of Mobile App Recommendations In-The-Wild. arXiv preprint arXiv:1505.03014 (2015)."},{"key":"e_1_3_2_1_3_1","unstructured":"Mathieu Blondel Akinori Fujino Naonori Ueda and Masakazu Ishihata. 2016. Higher-order factorization machines. In Advances in Neural Information Processing Systems. 3351--3359."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_5_1","volume-title":"Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart.","author":"Choi Edward","year":"2016","unstructured":"Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. 2016. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. In NIPS. 3504--3512."},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction. arXiv preprint arXiv:1704.05194","author":"Gai Kun","year":"2017","unstructured":"Kun Gai, Xiaoqiang Zhu, Han Li, Kai Liu, and Zhe Wang. 2017. Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction. arXiv preprint arXiv:1704.05194 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI . 1725--1731.","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_1_10_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis)","author":"Maxwell Harper F","year":"2016","unstructured":"F Maxwell Harper and Joseph A Konstan. 2016. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis) , Vol. 5, 4 (2016), 19."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","unstructured":"Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In SIGIR. ACM."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"e_1_3_2_1_15_1","volume-title":"Attention-based Deep Multiple Instance Learning. ICML","author":"Ilse Maximilian","year":"2018","unstructured":"Maximilian Ilse, Jakub M Tomczak, and Max Welling. 2018. Attention-based Deep Multiple Instance Learning. ICML (2018)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_1_17_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_1_18_1","doi-asserted-by":"crossref","unstructured":"Mu Li Ziqi Liu Alexander J. Smola and Yu-Xiang Wang. 2016. DiFacto: Distributed Factorization Machines. In WSDM. 377--386.","DOI":"10.1145\/2835776.2835781"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Jianxun Lian Xiaohuan Zhou Fuzheng Zhang Zhongxia Chen Xing Xie and Guangzhong Sun. 2018. xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems. In KDD . 1754--1763.","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_1_20_1","volume-title":"An efficacy driven approach for medication recommendation in type 2 diabetes treatment using data mining techniques. Studies in health technology and informatics","author":"Liu Haifeng","year":"2013","unstructured":"Haifeng Liu, Guotong Xie, Jing Mei, Weijia Shen, Wen Sun, and Xiang Li. 2013. An efficacy driven approach for medication recommendation in type 2 diabetes treatment using data mining techniques. Studies in health technology and informatics , Vol. 192 (2013), 1071--1071."},{"key":"e_1_3_2_1_21_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. In Advances In Neural Information Processing Systems. 289--297."},{"key":"e_1_3_2_1_22_1","volume-title":"Multilingual hierarchical attention networks for document classification. arXiv preprint arXiv:1707.00896","author":"Pappas Nikolaos","year":"2017","unstructured":"Nikolaos Pappas and Andrei Popescu-Belis. 2017. Multilingual hierarchical attention networks for document classification. arXiv preprint arXiv:1707.00896 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Product-based neural networks for user response prediction","author":"Qu Yanru","unstructured":"Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. 2016. Product-based neural networks for user response prediction. In ICDM. IEEE, 1149--1154."},{"key":"e_1_3_2_1_24_1","volume-title":"Factorization machines","author":"Rendle Steffen","unstructured":"Steffen Rendle. 2010. Factorization machines. In ICDM. IEEE, 995--1000."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Matthew Richardson Ewa Dominowska and Robert Ragno. 2007. Predicting clicks: estimating the click-through rate for new ads. In WWW . 521--530.","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939704"},{"key":"e_1_3_2_1_27_1","volume-title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks. arXiv preprint arXiv:1810.11921","author":"Song Weiping","year":"2018","unstructured":"Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, and Jian Tang. 2018. AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks. arXiv preprint arXiv:1810.11921 (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6449"},{"key":"e_1_3_2_1_29_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS. 5998--6008."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186175"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Deep & Cross Network for Ad Click Predictions","volume":"12","author":"Wang Ruoxi","year":"2017","unstructured":"Ruoxi Wang, Bin Fu, Gang Fu, and Mingliang Wang. 2017. Deep & Cross Network for Ad Click Predictions. In ADKDD. ACM, 12:1--12:7.","journal-title":"ADKDD. ACM"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Jun Xiao Hao Ye Xiangnan He Hanwang Zhang Fei Wu and Tat-Seng Chua. 2017. Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks. In IJCAI. 3119--3125.","DOI":"10.24963\/ijcai.2017\/435"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 842--850","author":"Xiao Tianjun","year":"2015","unstructured":"Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, and Zheng Zhang. 2015. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 842--850."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Haochao Ying Fuzhen Zhuang Fuzheng Zhang Yanchi Liu Guandong Xu Xing Xie Hui Xiong and Jian Wu. 2018. Sequential recommender system based on hierarchical attention networks. In IJCAI .","DOI":"10.24963\/ijcai.2018\/546"},{"key":"e_1_3_2_1_36_1","volume-title":"Xing Xie, and Zhenhui Li.","author":"Zheng Guanjie","year":"2018","unstructured":"Guanjie Zheng, Fuzheng Zhang, Zihan Zheng, Yang Xiang, Nicholas Jing Yuan, Xing Xie, and Zhenhui Li. 2018. Drn: A deep reinforcement learning framework for news recommendation. In WWW . 167--176."},{"key":"e_1_3_2_1_37_1","volume-title":"Deep Interest Evolution Network for Click-Through Rate Prediction. arXiv preprint arXiv:1809.03672","author":"Zhou Guorui","year":"2018","unstructured":"Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. 2018a. Deep Interest Evolution Network for Click-Through Rate Prediction. arXiv preprint arXiv:1809.03672 (2018)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Xiaoqiang Zhu Chengru Song Ying Fan Han Zhu Xiao Ma Yanghui Yan Junqi Jin Han Li and Kun Gai. 2018b. Deep Interest Network for Click-Through Rate Prediction. In KDD. 1059--1068.","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_39_1","unstructured":"D\u00e1vid Zibriczky. 2016. Recommender systems meet finance: a literature review. (2016)."}],"event":{"name":"WSDM '20: The Thirteenth ACM International Conference on Web Search and Data Mining","location":"Houston TX USA","acronym":"WSDM '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 13th International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3336191.3371785","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3336191.3371785","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3336191.3371785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T20:46:31Z","timestamp":1755809191000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3336191.3371785"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,20]]},"references-count":39,"alternative-id":["10.1145\/3336191.3371785","10.1145\/3336191"],"URL":"https:\/\/doi.org\/10.1145\/3336191.3371785","relation":{},"subject":[],"published":{"date-parts":[[2020,1,20]]},"assertion":[{"value":"2020-01-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}