{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:21:02Z","timestamp":1784092862472,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"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":[[2020,8,23]]},"DOI":"10.1145\/3394486.3403309","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T23:03:55Z","timestamp":1597964635000},"page":"2590-2598","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":54,"title":["Privileged Features Distillation at Taobao Recommendations"],"prefix":"10.1145","author":[{"given":"Chen","family":"Xu","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Ge","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyang","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyong","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changhua","family":"Pei","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Sun","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxiao","family":"Sun","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Ou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Rohan Anil Gabriel Pereyra Alexandre Passos Robert Ormandi George E Dahl and Geoffrey E Hinton. 2018. Large scale distributed neural network training through online distillation. In ICLR. Rohan Anil Gabriel Pereyra Alexandre Passos Robert Ormandi George E Dahl and Geoffrey E Hinton. 2018. Large scale distributed neural network training through online distillation. In ICLR."},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Cristian Bucilu? Rich Caruana and Alexandru Niculescu-Mizil. 2006. Model compression. In SIGKDD. ACM 535--541. Cristian Bucilu? Rich Caruana and Alexandru Niculescu-Mizil. 2006. Model compression. In SIGKDD. ACM 535--541.","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3281659"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Paul Covington Jay Adams and Emre Sargin. 2016. Deep neural networks for youtube recommendations. In RecSys. ACM 191--198. Paul Covington Jay Adams and Emre Sargin. 2016. Deep neural networks for youtube recommendations. In RecSys. ACM 191--198.","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"e_1_3_2_1_8_1","volume-title":"et almbox","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean , Greg Corrado , Rajat Monga , Kai Chen , Matthieu Devin , Mark Mao , Andrew Senior , Paul Tucker , Ke Yang , Quoc V Le , et almbox . 2012 . Large scale distributed deep networks. In NeurIPS. 1223--1231. Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Andrew Senior, Paul Tucker, Ke Yang, Quoc V Le, et almbox. 2012. Large scale distributed deep networks. In NeurIPS. 1223--1231."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/963770.963776"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_3_2_1_11_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 AAAI. 1725--1731. Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: A factorization-machine based neural network for CTR prediction. In AAAI. 1725--1731.","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_1_12_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778. Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_13_1","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2016. Session-based recommendations with recurrent neural networks. In ICLR. Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2016. Session-based recommendations with recurrent neural networks. In ICLR."},{"key":"e_1_3_2_1_14_1","volume-title":"Distilling the knowledge in a neural network. arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . 2015. Distilling the knowledge in a neural network. arXiv:1503.02531 ( 2015 ). Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Po-Sen Huang Xiaodong He Jianfeng Gao Li Deng Alex Acero and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In CIKM. ACM 2333--2338. Po-Sen Huang Xiaodong He Jianfeng Gao Li Deng Alex Acero and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In CIKM. ACM 2333--2338.","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_18_1","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML. 448--456. Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML. 448--456."},{"key":"e_1_3_2_1_19_1","volume-title":"2018 Self-attentive sequential recommendation","author":"Kang Wang-Cheng","unstructured":"Wang-Cheng Kang and Julian McAuley . 2018 Self-attentive sequential recommendation . In ICDM. IEEE , 197--206. Wang-Cheng Kang and Julian McAuley. 2018 Self-attentive sequential recommendation. In ICDM. IEEE, 197--206."},{"key":"e_1_3_2_1_20_1","volume-title":"Rush","author":"Kim Yoon","year":"2016","unstructured":"Yoon Kim and Alexander M . Rush . 2016 . Sequence-Level Knowledge Distillation. In EMNLP. 1317--1327. Yoon Kim and Alexander M. Rush. 2016. Sequence-Level Knowledge Distillation. In EMNLP. 1317--1327."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"John Lambert Ozan Sener and Silvio Savarese. 2018. Deep learning under privileged information using heteroscedastic dropout. In CVPR. 8886--8895. John Lambert Ozan Sener and Silvio Savarese. 2018. Deep learning under privileged information using heteroscedastic dropout. In CVPR. 8886--8895.","DOI":"10.1109\/CVPR.2018.00926"},{"key":"e_1_3_2_1_22_1","volume-title":"SIGKDD. ACM","author":"Lian Jianxun","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 SIGKDD. ACM , NY , USA , 1754--1763. 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 SIGKDD. ACM, NY, USA, 1754--1763."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-017-1836-5"},{"key":"e_1_3_2_1_24_1","unstructured":"Shichen Liu Fei Xiao Wenwu Ou and Luo Si. 2017. Cascade ranking for operational e-commerce search. In SIGKDD. ACM 1557--1565. Shichen Liu Fei Xiao Wenwu Ou and Luo Si. 2017. Cascade ranking for operational e-commerce search. In SIGKDD. ACM 1557--1565."},{"key":"e_1_3_2_1_25_1","unstructured":"David Lopez-Paz L\u00e9on Bottou Bernhard Sch\u00f6lkopf and Vladimir Vapnik. 2016. Unifying distillation and privileged information. In ICLR. David Lopez-Paz L\u00e9on Bottou Bernhard Sch\u00f6lkopf and Vladimir Vapnik. 2016. Unifying distillation and privileged information. In ICLR."},{"key":"e_1_3_2_1_26_1","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"Maas Andrew L","year":"2013","unstructured":"Andrew L Maas , Awni Y Hannun , and Andrew Y Ng . 2013 . Rectifier nonlinearities improve neural network acoustic models . In ICML , Vol. 30. 3 . Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In ICML, Vol. 30. 3.","journal-title":"ICML"},{"key":"e_1_3_2_1_27_1","volume-title":"et almbox","author":"McMahan H Brendan","year":"2013","unstructured":"H Brendan McMahan , Gary Holt , David Sculley , Michael Young , Dietmar Ebner , Julian Grady , Lan Nie , Todd Phillips , Eugene Davydov , Daniel Golovin , et almbox . 2013 . ftrl. In SIGKDD. 1222--1230. H Brendan McMahan, Gary Holt, David Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, et almbox. 2013. ftrl. In SIGKDD. 1222--1230."},{"key":"e_1_3_2_1_28_1","volume-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy. In ICLR.","author":"Mishra Asit","year":"2018","unstructured":"Asit Mishra and Debbie Marr . 2018 . Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy. In ICLR. Asit Mishra and Debbie Marr. 2018. Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy. In ICLR."},{"key":"e_1_3_2_1_29_1","unstructured":"Yabo Ni Dan Ou Shichen Liu Xiang Li Wenwu Ou Anxiang Zeng and Luo Si. 2018. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks. In SIGKDD. ACM 596--605. Yabo Ni Dan Ou Shichen Liu Xiang Li Wenwu Ou Anxiang Zeng and Luo Si. 2018. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks. In SIGKDD. ACM 596--605."},{"key":"e_1_3_2_1_30_1","volume-title":"Regularizing neural networks by penalizing confident output distributions. arXiv:1701.06548","author":"Pereyra Gabriel","year":"2017","unstructured":"Gabriel Pereyra , George Tucker , Jan Chorowski , \u0141ukasz Kaiser , and Geoffrey Hinton . 2017. Regularizing neural networks by penalizing confident output distributions. arXiv:1701.06548 ( 2017 ). Gabriel Pereyra, George Tucker, Jan Chorowski, \u0141ukasz Kaiser, and Geoffrey Hinton. 2017. Regularizing neural networks by penalizing confident output distributions. arXiv:1701.06548 (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015 . Fitnets : Hints for thin deep nets. In ICLR. Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. Fitnets: Hints for thin deep nets. In ICLR."},{"key":"e_1_3_2_1_32_1","volume-title":"An overview of multi-task learning in deep neural networks. arXiv:1706.05098","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder . 2017. An overview of multi-task learning in deep neural networks. arXiv:1706.05098 ( 2017 ). Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv:1706.05098 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jon Shlens and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision. In CVPR. 2818--2826. Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jon Shlens and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision. In CVPR. 2818--2826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Jiaxi Tang and Ke Wang. 2018. Ranking distillation: Learning compact ranking models with high performance for recommender system. In SIGKDD. ACM 2289--2298. Jiaxi Tang and Ke Wang. 2018. Ranking distillation: Learning compact ranking models with high performance for recommender system. In SIGKDD. ACM 2289--2298.","DOI":"10.1145\/3219819.3220021"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886814"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.042"},{"key":"e_1_3_2_1_37_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 NeurIPS. 5998--6008. 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 NeurIPS. 5998--6008."},{"key":"e_1_3_2_1_38_1","volume-title":"Kdgan: Knowledge distillation with generative adversarial networks. In NeurIPS. 775--786.","author":"Wang Xiaojie","year":"2018","unstructured":"Xiaojie Wang , Rui Zhang , Yu Sun , and Jianzhong Qi . 2018 . Kdgan: Knowledge distillation with generative adversarial networks. In NeurIPS. 775--786. Xiaojie Wang, Rui Zhang, Yu Sun, and Jianzhong Qi. 2018. Kdgan: Knowledge distillation with generative adversarial networks. In NeurIPS. 775--786."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang Tao Xiang Timothy M Hospedales and Huchuan Lu. 2018. Deep mutual learning. In CVPR. 4320--4328. Ying Zhang Tao Xiang Timothy M Hospedales and Huchuan Lu. 2018. Deep mutual learning. In CVPR. 4320--4328.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Ying Fan Runpeng Cui Weijie Bian Xiaoqiang Zhu and Kun Gai. 2018a. Rocket launching: A universal and efficient framework for training well-performing light net. In AAAI. Guorui Zhou Ying Fan Runpeng Cui Weijie Bian Xiaoqiang Zhu and Kun Gai. 2018a. Rocket launching: A universal and efficient framework for training well-performing light net. In AAAI.","DOI":"10.1609\/aaai.v32i1.11601"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Guorui Zhou Xiaoqiang Zhu Chenru 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 SIGKDD. ACM 1059--1068. Guorui Zhou Xiaoqiang Zhu Chenru 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 SIGKDD. ACM 1059--1068.","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event CA USA","acronym":"KDD '20","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 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403309","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394486.3403309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:48Z","timestamp":1750197708000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":41,"alternative-id":["10.1145\/3394486.3403309","10.1145\/3394486"],"URL":"https:\/\/doi.org\/10.1145\/3394486.3403309","relation":{},"subject":[],"published":{"date-parts":[[2020,8,20]]},"assertion":[{"value":"2020-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}