{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:42:23Z","timestamp":1783438943844,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"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":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462976","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:54Z","timestamp":1626057714000},"page":"1269-1278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["ScaleFreeCTR: MixCache-based Distributed Training System for CTR Models with Huge Embedding Table"],"prefix":"10.1145","author":[{"given":"Huifeng","family":"Guo","sequence":"first","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Gao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiming","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuqiang","family":"He","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhi","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart'in","year":"2016","unstructured":"Mart'in Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 265--283."},{"key":"e_1_3_2_2_2_1","volume-title":"Language Models are Few-Shot Learners. CoRR","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. CoRR, Vol. abs\/2005.14165 (2020)."},{"key":"e_1_3_2_2_3_1","volume-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","author":"Chen Tianqi","year":"2015","unstructured":"Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172127"},{"key":"e_1_3_2_2_7_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li Xiuqiang He and Zhenhua Dong. 2018. DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction. CoRR Vol. abs\/1804.04950 (2018). arxiv: 1804.04950 http:\/\/arxiv.org\/abs\/1804.04950"},{"key":"e_1_3_2_2_8_1","unstructured":"Huifeng Guo Jinkai Yu Qing Liu Ruiming Tang and Yuzhou Zhang. 2019. PAL: a position-bias aware learning framework for CTR prediction in live recommender systems. In RecSys. ACM 452--456."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0028"},{"key":"e_1_3_2_2_10_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27--30, 2016. IEEE Computer Society, 770--778."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_2_12_1","unstructured":"J. B. Heaton Nicholas G. Polson and J. H. Witte. 2016. Deep Learning in Finance. CoRR Vol. abs\/1602.06561 (2016)."},{"key":"e_1_3_2_2_13_1","volume-title":"Phillip B. Gibbons, Garth A. Gibson, Gregory R. Ganger, and Eric P. Xing.","author":"Ho Qirong","year":"2013","unstructured":"Qirong Ho, James Cipar, Henggang Cui, Seunghak Lee, Jin Kyu Kim, Phillip B. Gibbons, Garth A. Gibson, Gregory R. Ganger, and Eric P. Xing. 2013. More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server. In Advances in Neural Information Processing Systems. 1223--1231."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347043"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341255"},{"key":"e_1_3_2_2_16_1","volume-title":"Le","author":"Joglekar Manas R.","year":"2019","unstructured":"Manas R. Joglekar, Cong Li, Jay K. Adams, Pranav Khaitan, and Quoc V. Le. 2019. Neural Input Search for Large Scale Recommendation Models. CoRR, Vol. abs\/1907.04471 (2019). arxiv: 1907.04471 http:\/\/arxiv.org\/abs\/1907.04471"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Yu-Chin Juan Yong Zhuang Wei-Sheng Chin and Chih-Jen Lin. 2016. Field-aware Factorization Machines for CTR Prediction. In In RecSys. 43--50.","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303957"},{"key":"e_1_3_2_2_19_1","volume-title":"PyTorch-BigGraph: A Large-scale Graph Embedding System. arXiv preprint arXiv:1903.12287","author":"Lerer Adam","year":"2019","unstructured":"Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, and Alex Peysakhovich. 2019. PyTorch-BigGraph: A Large-scale Graph Embedding System. arXiv preprint arXiv:1903.12287 (2019)."},{"key":"e_1_3_2_2_20_1","volume-title":"Scaling Distributed Machine Learning with the Parameter Server. In 11th USENIX Symposium on Operating Systems Design and Implementation, Jason Flinn and Hank Levy (Eds.). USENIX Association, 583--598","author":"Li Mu","year":"2014","unstructured":"Mu Li, David G. Andersen, Jun Woo Park, Alexander J. Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J. Shekita, and Bor-Yiing Su. 2014. Scaling Distributed Machine Learning with the Parameter Server. In 11th USENIX Symposium on Operating Systems Design and Implementation, Jason Flinn and Hank Levy (Eds.). USENIX Association, 583--598."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313497"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401082"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of International Conference on Cluster Computing. IEEE Computer Society, 135--144","author":"Mamidala Amith R.","unstructured":"Amith R. Mamidala, Jiuxing Liu, and Dhabaleswar K. Panda. 2004. Efficient Barrier and Allreduce on Infiniband clusters using multicast and adaptive algorithms. In Proceedings of International Conference on Cluster Computing. IEEE Computer Society, 135--144."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"H Brendan McMahan Gary Holt David Sculley Michael Young Dietmar Ebner Julian Grady Lan Nie Todd Phillips Eugene Davydov Daniel Golovin et al. 2013. Ad click prediction: a view from the trenches. In SIGKDD. ACM 1222--1230.","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_2_26_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson G. Azzolini Dmytro Dzhulgakov Andrey Mallevich Ilia Cherniavskii Yinghai Lu Raghuraman Krishnamoorthi Ansha Yu Volodymyr Kondratenko Stephanie Pereira Xianjie Chen Wenlin Chen Vijay Rao Bill Jia Liang Xiong and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR Vol. abs\/1906.00091 (2019)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233770"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401113"},{"key":"e_1_3_2_2_31_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. CoRR","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. CoRR, Vol. abs\/1802.05799 (2018). http:\/\/arxiv.org\/abs\/1802.05799"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_2_34_1","volume-title":"A Practical Incremental Method to Train Deep CTR Models. CoRR","author":"Wang Yichao","year":"2020","unstructured":"Yichao Wang, Huifeng Guo, Ruiming Tang, Zhirong Liu, and Xiuqiang He. 2020. A Practical Incremental Method to Train Deep CTR Models. CoRR, Vol. abs\/2009.02147 (2020)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412754"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330865"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Rex Ying Ruining He Kaifeng Chen Pong Eksombatchai William L. Hamilton and Jure Leskovec. 2018. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. In SIGKDD. ACM 974--983.","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_4"},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of Machine Learning and Systems","author":"Zhao Weijie","year":"2020","unstructured":"Weijie Zhao, Deping Xie, Ronglai Jia, Yulei Qian, Ruiquan Ding, Mingming Sun, and Ping Li. 2020. Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems. In Proceedings of Machine Learning and Systems 2020, Inderjit S. Dhillon, Dimitris S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462976","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:20Z","timestamp":1750191500000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462976"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":41,"alternative-id":["10.1145\/3404835.3462976","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462976","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}