{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:15:01Z","timestamp":1775283301504,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"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":[[2022,6,10]]},"DOI":"10.1145\/3514221.3517902","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"470-480","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["HET-GMP: A Graph-based System Approach to Scaling Large Embedding Model Training"],"prefix":"10.1145","author":[{"given":"Xupeng","family":"Miao","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Yining","family":"Shi","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Hailin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Xiaonan","family":"Nie","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Zhi","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"given":"Bin","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2014. The Apache Giraph Project. http:\/\/giraph.apache.org\/."},{"key":"e_1_3_2_2_2_1","unstructured":"2014. Criteo Kaggle Ad. https:\/\/www.kaggle.com\/c\/criteo-display-ad-challenge."},{"key":"e_1_3_2_2_3_1","unstructured":"2015. Avazu Ad. http:\/\/www.kaggle.com\/c\/avazu-ctr-prediction."},{"key":"e_1_3_2_2_4_1","unstructured":"2020. MLPerf Benchmark. https:\/\/mlperf.org."},{"key":"e_1_3_2_2_5_1","unstructured":"2021. Hetu. https:\/\/github.com\/PKU-DAIR\/Hetu\/."},{"key":"e_1_3_2_2_6_1","unstructured":"2021. NVIDIA collective communications library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_2_7_1","unstructured":"2021. NVIDIA HugeCTR. https:\/\/github.com\/NVIDIA\/HugeCTR."},{"key":"e_1_3_2_2_8_1","volume-title":"Benoit Steiner, Paul A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng.","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek Gordon Murray, Benoit Steiner, Paul A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In OSDI. USENIX Association, 265--283."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/170035.170072"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0701--9"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-015--1501-x"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741970"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Heng-Tze Cheng Levent Koc Jeremiah Harmsen Tal Shaked Tushar Chandra Hrishi Aradhye Glen Anderson Greg Corrado Wei Chai Mustafa Ispir Rohan Anil Zakaria Haque Lichan Hong Vihan Jain Xiaobing Liu and Hemal Shah. 2016. Wide & Deep Learning for Recommender Systems. In DLRS@RecSys. 7--10.","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_14_1","volume-title":"cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2952-7"},{"key":"e_1_3_2_2_18_1","volume-title":"PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs","author":"Gonzalez Joseph E.","unstructured":"Joseph E. Gonzalez, Yucheng Low, Haijie Gu, Danny Bickson, and Carlos Guestrin. 2012. PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In OSDI. USENIX Association, 17--30."},{"key":"e_1_3_2_2_19_1","volume-title":"GraphX: Graph Processing in a Distributed Dataflow Framework","author":"Gonzalez Joseph E.","unstructured":"Joseph E. Gonzalez, Reynold S. Xin, Ankur Dave, Daniel Crankshaw, Michael J. Franklin, and Ion Stoica. 2014. GraphX: Graph Processing in a Distributed Dataflow Framework. In OSDI. USENIX Association, 599--613."},{"key":"e_1_3_2_2_20_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_2_21_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 NeurIPS. 1223--1231."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303957"},{"key":"e_1_3_2_2_24_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR. OpenReview.net."},{"key":"e_1_3_2_2_25_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 OSDI. USENIX Association, 583--598."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","unstructured":"Zeyu Li Wei Cheng Yang Chen Haifeng Chen and Wei Wang. 2020. Interpretable Click-Through Rate Prediction through Hierarchical Attention. In WSDM. ACM 313--321. https:\/\/doi.org\/10.1145\/3336191.3371785","DOI":"10.1145\/3336191.3371785"},{"key":"e_1_3_2_2_28_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 SIGKDD. 1754--1763.","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_2_29_1","unstructured":"Xiangru Lian Yijun Huang Yuncheng Li and Ji Liu. 2015. Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization. In NeurIPS. 2737--2745."},{"key":"e_1_3_2_2_30_1","volume-title":"ICML","volume":"80","author":"Lian Xiangru","year":"2018","unstructured":"Xiangru Lian, Wei Zhang, Ce Zhang, and Ji Liu. 2018. Asynchronous Decentralized Parallel Stochastic Gradient Descent. In ICML, Vol. 80. PMLR, 3049--3058."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","unstructured":"Xupeng Miao Nezihe Merve G\u00fcrel Wentao Zhang Zhichao Han Bo Li Wei Min Susie Xi Rao Hansheng Ren Yinan Shan Yingxia Shao Yujie Wang Fan Wu Hui Xue Yaming Yang Zitao Zhang Yang Zhao Shuai Zhang Yujing Wang Bin Cui and Ce Zhang. 2021. DeGNN: Improving Graph Neural Networks with Graph Decomposition. In SIGKDD. ACM 1223--1233. https:\/\/doi.org\/10.1145\/3447548.3467312","DOI":"10.1145\/3447548.3467312"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452773"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489511"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3103984"},{"key":"e_1_3_2_2_36_1","unstructured":"Dheevatsa Mudigere Yuchen Hao Jianyu Huang Andrew Tulloch Srinivas Sridharan Xing Liu Mustafa Ozdal Jade Nie Jongsoo Park Liang Luo Jie Amy Yang Leon Gao Dmytro Ivchenko Aarti Basant Yuxi Hu Jiyan Yang Ehsan K. Ardestani Xiaodong Wang Rakesh Komuravelli Ching-Hsiang Chu Serhat Yilmaz Huayu Li Jiyuan Qian Zhuobo Feng Yinbin Ma Junjie Yang Ellie Wen Hong Li Lin Yang Chonglin Sun Whitney Zhao Dimitry Melts Krishna Dhulipala K. R. Kishore Tyler Graf Assaf Eisenman Kiran Kumar Matam Adi Gangidi Guoqiang Jerry Chen Manoj Krishnan Avinash Nayak Krishnakumar Nair Bharath Muthiah Mahmoud khorashadi Pallab Bhattacharya Petr Lapukhov Maxim Naumov Lin Qiao Mikhail Smelyanskiy Bill Jia and Vijay Rao. 2021. High-performance Distributed Training of Large-scale Deep Learning Recommendation Models. CoRR abs\/2104.05158 (2021). arXiv:2104.05158"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020--3219--6"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476325"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407796"},{"key":"e_1_3_2_2_40_1","volume-title":"Nicolas Le Roux, and Francis R. Bach","author":"Schmidt Mark","year":"2011","unstructured":"Mark Schmidt, Nicolas Le Roux, and Francis R. Bach. 2011. Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization. In NeurIPS. 1458--1466."},{"key":"e_1_3_2_2_41_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. 12:1--12:7.","journal-title":"ADKDD."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457564"},{"key":"e_1_3_2_2_43_1","unstructured":"Qiyu Wu Chen Xing Yatao Li Guolin Ke Di He and Tie-Yan Liu. 2021. Taking Notes on the Fly Helps Language Pre-Training. In ICLR. OpenReview.net."},{"key":"e_1_3_2_2_44_1","unstructured":"Cong Xie Ling Yan Wu-Jun Li and Zhihua Zhang. 2014. Distributed Power-law Graph Computing: Theoretical and Empirical Analysis. In NeurIPS. 1673--1681."},{"key":"e_1_3_2_2_45_1","unstructured":"Minhui Xie Kai Ren Youyou Lu Guangxu Yang Qingxing Xu Bihai Wu Jiazhen Lin Hongbo Ao Wanhong Xu and Jiwu Shu. 2020. Kraken: memory-efficient continual learning for large-scale real-time recommendations. In SC. 21."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","unstructured":"Zhiqiang Xu Dong Li Weijie Zhao Xing Shen Tianbo Huang Xiaoyun Li and Ping Li. 2021. Agile and Accurate CTR Prediction Model Training for Massive- Scale Online Advertising Systems. In SIGMOD. ACM 2404--2409. https:\/\/doi.org\/10.1145\/3448016.3457236","DOI":"10.1145\/3448016.3457236"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137649"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Wentao Zhang Xupeng Miao Yingxia Shao Jiawei Jiang Lei Chen Olivier Ruas and Bin Cui. 2020. Reliable data distillation on graph convolutional network. In SIGMOD. 1399--1414.","DOI":"10.1145\/3318464.3389706"},{"key":"e_1_3_2_2_50_1","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 MLSys. mlsys.org."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Da Zheng Chao Ma Minjie Wang Jinjing Zhou Qidong Su Xiang Song Quan Gan Zheng Zhang and George Karypis. 2020. DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs. In IA3 Workshop. 36--44.","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Da Zheng Xiang Song Chao Ma Zeyuan Tan Zihao Ye Jin Dong Hao Xiong Zheng Zhang and George Karypis. 2020. DGL-KE: Training Knowledge Graph Embeddings at Scale. In SIGIR. ACM 739--748.","DOI":"10.1145\/3397271.3401172"},{"key":"e_1_3_2_2_53_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. 2018. Deep Interest Network for Click-Through Rate Prediction. In SIGKDD. 1059--1068.","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_2_54_1","volume-title":"Xing","author":"Zhou Yi","year":"2016","unstructured":"Yi Zhou, Yaoliang Yu, Wei Dai, Yingbin Liang, and Eric P. Xing. 2016. On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System. In AISTATS, Arthur Gretton and Christian C. Robert (Eds.), Vol. 51. JMLR.org, 713--722."}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517902","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3517902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:06Z","timestamp":1750183806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3517902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":52,"alternative-id":["10.1145\/3514221.3517902","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3517902","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}