{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T11:29:52Z","timestamp":1782818992656,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"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\/3534678.3539070","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"3288-3298","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters"],"prefix":"10.1145","author":[{"given":"Xiangru","family":"Lian","sequence":"first","affiliation":[{"name":"Kwai Inc, Seattle , WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binhang","family":"Yuan","sequence":"additional","affiliation":[{"name":"ETH, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulong","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjun","family":"He","sequence":"additional","affiliation":[{"name":"ETH, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haodong","family":"Lyu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Dong","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiao","family":"Liao","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingnan","family":"Luo","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingru","family":"Xie","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianying","family":"Lin","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengchun","family":"Shu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuezhong","family":"Qiu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhishan","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijng, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongying","family":"Kong","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yuan","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Yu","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Kwai Inc, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"(n.d.) Avazu CTR. www.kaggle.com\/c\/avazu-ctr-prediction."},{"key":"e_1_3_2_1_2_1","unstructured":"(n.d.) Criteo CTR. ailab.criteo.com\/download-criteo-1tb-click-logs-dataset."},{"key":"e_1_3_2_1_3_1","unstructured":"(n.d.) Parallel Distributed Deep Learning: Machine Learning Framework from Industrial Practice. https:\/\/www.paddlepaddle.org.cn\/."},{"key":"e_1_3_2_1_4_1","unstructured":"(n.d.) Taobao CTR. www.kaggle.com\/pavansanagapati\/ad-displayclick-dataon-taobaocom."},{"key":"e_1_3_2_1_5_1","volume-title":"Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981","author":"Chen Jianmin","year":"2016","unstructured":"Jianmin Chen, Xinghao Pan, Rajat Monga, Samy Bengio, and Rafal Jozefowicz. 2016. Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981 (2016)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080797"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864770"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186183"},{"key":"e_1_3_2_1_11_1","volume-title":"BAGUA: Scaling up Distributed Learning with System Relaxations. arXiv preprint arXiv:2107.01499","author":"Gan Shaoduo","year":"2021","unstructured":"Shaoduo Gan, Xiangru Lian, Rui Wang, Jianbin Chang, Chengjun Liu, Hongmei Shi, Shengzhuo Zhang, Xianghong Li, Tengxu Sun, Jiawei Jiang, et al. 2021. BAGUA: Scaling up Distributed Learning with System Relaxations. arXiv preprint arXiv:2107.01499 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2843948"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883006"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341255"},{"key":"e_1_3_2_1_15_1","volume-title":"Alexander J Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J Shekita, and Bor-Yiing Su.","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 ({OSDI} 14). 583--598."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220014"},{"key":"e_1_3_2_1_17_1","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","volume":"28","author":"Lian Xiangru","year":"2015","unstructured":"Xiangru Lian, Yijun Huang, Yuncheng Li, and Ji Liu. 2015. Asynchronous parallel stochastic gradient for nonconvex optimization. Advances in Neural Information Processing Systems 28 (2015), 2737--2745.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","volume-title":"A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order. NIPS","author":"Lian Xiangru","year":"2016","unstructured":"Xiangru Lian, Huan Zhang, Cho-Jui Hsieh, Yijun Huang, and Ji Liu. 2016. A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order. NIPS (2016)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837018"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. VLDB Endow. https:\/\/doi.org\/10","author":"Miao Xupeng","year":"2022","unstructured":"Xupeng Miao, Hailin Zhang, Yining Shi, Xiaonan Nie, Zhi Yang, Yangyu Tao, and Bin Cui. 2022. HET: Scaling out Huge Embedding Model Training via Cacheenabled Distributed Framework. Proc. VLDB Endow. https:\/\/doi.org\/10.14778\/ 3489496.3489511"},{"key":"e_1_3_2_1_21_1","unstructured":"Dheevatsa Mudigere Yuchen Hao Jianyu Huang Andrew Tulloch Srinivas Sridharan Xing Liu Mustafa Ozdal Jade Nie Jongsoo Park Liang Luo et al. 2021. High-performance distributed training of large-scale deep learning recommendation models. arXiv preprint arXiv:2104.05158 (2021)."},{"key":"e_1_3_2_1_22_1","unstructured":"Maxim Naumov John Kim Dheevatsa Mudigere Srinivas Sridharan Xiaodong Wang Whitney Zhao Serhat Yilmaz Changkyu Kim Hector Yuen Mustafa Ozdal et al. 2020. Deep learning training in facebook data centers: Design of scale-up and scale-out systems. arXiv preprint arXiv:2003.09518 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems. 693--701","author":"Niu Feng","year":"2011","unstructured":"Feng Niu, Benjamin Recht, Christopher Re, and Stephen J Wright. 2011. HOGWILD! a lock-free approach to parallelizing stochastic gradient descent. In Proceedings of the 24th International Conference on Neural Information Processing Systems. 693--701."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330837"},{"key":"e_1_3_2_1_25_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106426.3109037"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988452"},{"key":"e_1_3_2_1_28_1","volume-title":"Neural Information Processing Systems Conference (NIPS","volume":"26","author":"Den Oord A\u00e4ron Van","year":"2013","unstructured":"A\u00e4ron Van Den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Neural Information Processing Systems Conference (NIPS 2013), Vol. 26. Neural Information Processing Systems Foundation (NIPS)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.04.018"},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Visual background recommendation for dance performances using deep matrix factorization","volume":"14","author":"She James","year":"2018","unstructured":"JiqingWen, James She, Xiaopeng Li, and Hui Mao. 2018. Visual background recommendation for dance performances using deep matrix factorization. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14, 1 (2018), 1--19.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"e_1_3_2_1_31_1","volume-title":"RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference. arXiv preprint arXiv:2102.00075","author":"Wilkening Mark","year":"2021","unstructured":"Mark Wilkening, Udit Gupta, Samuel Hsia, Caroline Trippel, Carole-Jean Wu, David Brooks, and Gu-Yeon Wei. 2021. RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference. arXiv preprint arXiv:2102.00075 (2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"Personalized recommendation systems: Five hot research topics you must know. Microsoft Research Lab-Asia","author":"Xie Xing","year":"2018","unstructured":"Xing Xie, Jianxun Lian, Zheng Liu, Xiting Wang, Fangzhao Wu, Hongwei Wang, and Zhongxia Chen. 2018. Personalized recommendation systems: Five hot research topics you must know. Microsoft Research Lab-Asia (2018)."},{"key":"e_1_3_2_1_33_1","volume-title":"Distributed hierarchical gpu parameter server for massive scale deep learning ads systems. arXiv preprint arXiv:2003.05622","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. arXiv preprint arXiv:2003.05622 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358045"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"}],"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\/3534678.3539070","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:50Z","timestamp":1750183790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":35,"alternative-id":["10.1145\/3534678.3539070","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539070","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"}}]}}