{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:49:00Z","timestamp":1783738140280,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3304700"],"award-info":[{"award-number":["2023YFC3304700"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272168"],"award-info":[{"award-number":["62272168"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["23ZR1419900"],"award-info":[{"award-number":["23ZR1419900"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Young Faculty Open Research Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3722212.3724454","type":"proceedings-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T09:00:26Z","timestamp":1750150826000},"page":"350-363","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Scheduling Data Processing Pipelines for Incremental Training on MLP-based Recommendation Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3681-9504","authenticated-orcid":false,"given":"Zihao","family":"Chen","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8265-8461","authenticated-orcid":false,"given":"Chenyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3429-4732","authenticated-orcid":false,"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0862-1093","authenticated-orcid":false,"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3170-3326","authenticated-orcid":false,"given":"Jiaqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4132-8630","authenticated-orcid":false,"given":"Weining","family":"Qian","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4665-7302","authenticated-orcid":false,"given":"Aoying","family":"Zhou","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 265--283","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 Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3485450.3485462"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613142"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 2023 ACM Symposium on Cloud Computing (SoCC). 358--375","author":"Audibert Andrew","unstructured":"Andrew Audibert, Yang Chen, Dan Graur, Ana Klimovic, Ji\u0159\u00ed \u0160im\u0161a, and Chandramohan A. Thekkath. 2023. tf.data service: A Case for Disaggregating ML Input Data Processing. In Proceedings of the 2023 ACM Symposium on Cloud Computing (SoCC). 358--375."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.2007.4295640"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105693"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462936"},{"key":"e_1_3_2_1_10_1","volume-title":"Introduction to Algorithms","author":"Cormen Thomas H.","unstructured":"Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, and Clifford Stein. 2009. Introduction to Algorithms, Third Edition 3rd ed.). The MIT Press.","edition":"3"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526186"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of Machine Learning and Systems (MLSys).","author":"Eisenman Assaf","year":"2019","unstructured":"Assaf Eisenman, Maxim Naumov, Darryl Gardner, Misha Smelyanskiy, Sergey Pupyrev, Kim M. Hazelwood, Asaf Cidon, and Sachin Katti. 2019. Bandana: Using Non-Volatile Memory for Storing Deep Learning Models. In Proceedings of Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_14_1","article-title":"The Netflix Recommender System: Algorithms, Business Value, and Innovation","volume":"6","author":"Gomez-Uribe Carlos A.","year":"2016","unstructured":"Carlos A. Gomez-Uribe and Neil Hunt. 2016. The Netflix Recommender System: Algorithms, Business Value, and Innovation. ACM Trans. Manage. Inf. Syst. (TMIS), Vol. 6, 4 (2016).","journal-title":"ACM Trans. Manage. Inf. Syst. (TMIS)"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574262"},{"key":"e_1_3_2_1_16_1","volume-title":"Sangeetha Abdu Jyothi, and Roy H. Campbell","author":"Hashemi Sayed Hadi","year":"2019","unstructured":"Sayed Hadi Hashemi, Sangeetha Abdu Jyothi, and Roy H. Campbell. 2019. TicTac: Accelerating Distributed Deep Learning with Communication Scheduling. In Proceedings of the 2019 Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467084"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517848"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547387"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2019 Machine Learning and Systems (MLSys).","author":"Jayarajan Anand","year":"2019","unstructured":"Anand Jayarajan, Jinliang Wei, Garth Gibson, Alexandra Fedorova, and Gennady Pekhimenko. 2019. Priority-based Parameter Propagation for Distributed DNN Training. In Proceedings of the 2019 Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_22_1","volume-title":"The Case for Unifying Data Loading in Machine Learning Clusters. In 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud).","author":"Kakaraparthy Aarati","year":"2019","unstructured":"Aarati Kakaraparthy, Abhay Venkatesh, Amar Phanishayee, and Shivaram Venkataraman. 2019. The Case for Unifying Data Loading in Machine Learning Clusters. In 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539070"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688111"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589310"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517902"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489511"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3446095.3446100"},{"key":"e_1_3_2_1_30_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 Vol. abs\/2104.05158 (2021). showeprint[arXiv]2104.05158"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476374"},{"key":"e_1_3_2_1_32_1","unstructured":"MXNet. 2024. Apache MXNet. https:\/\/mxnet.apache.org\/versions\/1.9.1."},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2024. Merlin HugeCTR. https:\/\/nvidia-merlin.github.io\/HugeCTR\/master\/index.html."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Yanghua Peng Yixin Bao Yangrui Chen Chuan Wu and Chuanxiong Guo. 2018. Optimus: an efficient dynamic resource scheduler for deep learning clusters (EuroSys). Article 3.","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_36_1","unstructured":"PyTorch. 2024a. CPU threading and TorchScript inference. https:\/\/pytorch.org\/docs\/stable\/notes\/cpu_threading_torchscript_inference.html."},{"key":"e_1_3_2_1_37_1","unstructured":"PyTorch. 2024b. PyTorch DataLoader. https:\/\/pytorch.org\/docs\/stable\/data.html##torch.utils.data.DataLoader."},{"key":"e_1_3_2_1_38_1","unstructured":"PyTorch. 2024c. PyTorch Repository. https:\/\/github.com\/pytorch\/pytorch."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507777"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437643"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2017.72"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613169"},{"key":"e_1_3_2_1_43_1","unstructured":"TensorFlow. 2024a. Set number of threads used for parallelism between independent operations. https:\/\/tensorflow.google.cn\/guide\/profiler."},{"key":"e_1_3_2_1_44_1","unstructured":"TensorFlow. 2024b. TensorFlow Recommenders Addons. https:\/\/github.com\/tensorflow\/recommenders-addons."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579083"},{"key":"e_1_3_2_1_46_1","volume-title":"Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation Gradient Descent. In 2023 USENIX Annual Technical Conference (USENIX ATC). 995--1008","author":"Weng Qizhen","year":"2023","unstructured":"Qizhen Weng, Lingyun Yang, Yinghao Yu, Wei Wang, Xiaochuan Tang, Guodong Yang, and Liping Zhang. 2023. Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation Gradient Descent. In 2023 USENIX Annual Technical Conference (USENIX ATC). 995--1008."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519554"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457566"},{"key":"e_1_3_2_1_49_1","volume-title":"Accelerating Neural Recommendation Training with Embedding Scheduling. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI). 1141--1156","author":"Zeng Chaoliang","year":"2024","unstructured":"Chaoliang Zeng, Xudong Liao, Xiaodian Cheng, Han Tian, Xinchen Wan, Hao Wang, and Kai Chen. 2024. Accelerating Neural Recommendation Training with Embedding Scheduling. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI). 1141--1156."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539034"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732977.2733001"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 2017 USENIX Annual Technical Conference, (USENIX ATC). 181--193","author":"Zhang Hao","unstructured":"Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, and Eric P. Xing. 2017. Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters. In Proceedings of the 2017 USENIX Annual Technical Conference, (USENIX ATC). 181--193."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403334"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/636"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589773"},{"key":"e_1_3_2_1_56_1","volume-title":"Understanding and Co-designing the Data Ingestion Pipeline for Industry-Scale RecSys Training. ArXiv","author":"Zhao Mark","year":"2021","unstructured":"Mark Zhao, Niket Agarwal, Aarti Basant, Bugra Gedik, Satadru Pan, Mustafa Ozdal, Rakesh Komuravelli, Jerry Pan, Tianshu Bao, Haowei Lu, Sundaram Narayanan, Jack Langman, Kevin Wilfong, Harsha Rastogi, Carole-Jean Wu, Christos Kozyrakis, and Parikshit Pol. 2021. Understanding and Co-designing the Data Ingestion Pipeline for Industry-Scale RecSys Training. ArXiv, Vol. abs\/2108.09373 (2021)."},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys.","author":"Zhao Mark","year":"2023","unstructured":"Mark Zhao, Dhruv Choudhary, Devashish Tyagi, Ajay Somani, Max Kaplan, Sung-Han Lin, Sarunya Pumma, Jongsoo Park, Aarti Basant, Niket Agarwal, Carole-Jean Wu, and Christos Kozyrakis. 2023a. RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure. In Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"}],"event":{"name":"SIGMOD\/PODS '25: International Conference on Management of Data","location":"Berlin Germany","acronym":"SIGMOD\/PODS '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the 2025 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3722212.3724454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:41:46Z","timestamp":1757544106000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722212.3724454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":58,"alternative-id":["10.1145\/3722212.3724454","10.1145\/3722212"],"URL":"https:\/\/doi.org\/10.1145\/3722212.3724454","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}