{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T23:44:29Z","timestamp":1765842269162,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,27]],"date-time":"2020-10-27T00:00:00Z","timestamp":1603756800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2019YFB1802800"],"award-info":[{"award-number":["2019YFB1802800"]}]},{"name":"National Science Fund of China","award":["61725206"],"award-info":[{"award-number":["61725206"]}]},{"name":"Youth Innovation Promotion Association CAS"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,27]]},"DOI":"10.1145\/3419394.3423637","type":"proceedings-article","created":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T20:30:22Z","timestamp":1603398622000},"page":"528-534","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Dissecting the Communication Latency in Distributed Deep Sparse Learning"],"prefix":"10.1145","author":[{"given":"Heng","family":"Pan","sequence":"first","affiliation":[{"name":"ICT, CAS, China and Purple Mountain Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"ICT, CAS, China and Purple Mountain Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JianBo","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Lan","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gareth","family":"Tyson","sequence":"additional","affiliation":[{"name":"QMUL, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaogang","family":"Xie","sequence":"additional","affiliation":[{"name":"CNIC, CAS, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. The Apache Software Foundation. Apache hadoop. http:\/\/hadoop.apache. org\/core\/.. ([n. d.])."},{"key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. Facebook Gloo. https:\/\/github.com\/facebookincubator\/gloo. ([n. d.])."},{"key":"e_1_3_2_2_3_1","unstructured":"[n. d.]. Microsoft multiverso. https:\/\/github.com\/Microsoft\/multiverso\/wiki.. ([n. d.])."},{"key":"e_1_3_2_2_4_1","unstructured":"[n. d.]. NVIDIA Collective Communication Library (NCCL). https:\/\/developer.nvidia.com\/nccl. ([n. d.])."},{"key":"e_1_3_2_2_5_1","volume-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems.1709--1720.","author":"Alistarh Dan","year":"2017","unstructured":"Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. 2017. QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems.1709--1720."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Ashish Goel Bahman Bahmani and Rajendra Shinde. 2012. Efficient distributed locality sensitive hashing. In ACM CIKM.","DOI":"10.1145\/2396761.2398596"},{"key":"e_1_3_2_2_7_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv: Computation and Language (2014)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"e_1_3_2_2_9_1","volume-title":"HaitaoWu and Marina Lipshteyn","author":"Gaurav Soni Jianxi Ye Zhong Deng","year":"2016","unstructured":"Zhong Deng Gaurav Soni Jianxi Ye Jitu Padhye Chuanxiong Guo, HaitaoWu and Marina Lipshteyn. 2016. RDMA over Commodity Ethernet at Scale. In ACM SIGCOMM."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_2_2_11_1","volume-title":"Priority-based parameter propagation for distributed DNN training. SysML","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. SysML (2019)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341255"},{"key":"e_1_3_2_2_13_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. (2012) 1097--1105."},{"key":"e_1_3_2_2_14_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_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJPP.0000029272.69895.c1"},{"key":"e_1_3_2_2_17_1","unstructured":"T. Das A. Dave J. M. Ma M. McCauley M. J. Franklin S. Shenker M. Zaharia M. Chowdhury and I. Stoica. 2012. Fast and interactive analytics over Hadoop data with Spark. In USENIX; login:."},{"volume-title":"7th {USENIX} Workshop on Hot Topics in Cloud Computing (HotCloud 15).","author":"Mai Luo","key":"e_1_3_2_2_18_1","unstructured":"Luo Mai, Chuntao Hong, and Paolo Costa. 2015. Optimizing network performance in distributed machine learning. In 7th {USENIX} Workshop on Hot Topics in Cloud Computing (HotCloud 15)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Hasim Sak Andrew W Senior and Francoise Beaufays. 2014. Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling. (2014) 338--342.","DOI":"10.21437\/Interspeech.2014-80"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"e_1_3_2_2_22_1","volume-title":"Dan RK Ports, and Peter Richt\u00e1rik","author":"Sapio Amedeo","year":"2019","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan RK Ports, and Peter Richt\u00e1rik. 2019. Scaling distributed machine learning with in-network aggregation. arXiv preprint arXiv:1903.06701 (2019)."},{"key":"e_1_3_2_2_23_1","volume-title":"Campbell","author":"Jyothi Sayed Hadi Hashemi Sangeetha Abdu","year":"2019","unstructured":"Sangeetha Abdu Jyothi Sayed Hadi Hashemi and Roy H. Campbell. 2019. TicTac: Accelerating distributed deep learning with communication scheduling. SysML (2019)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306025"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303979"},{"key":"e_1_3_2_2_26_1","volume-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in neural information processing systems.1509--1519.","author":"Wen Wei","year":"2017","unstructured":"Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2017. Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in neural information processing systems.1509--1519."},{"volume-title":"Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters. In 2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Zhang Hao","key":"e_1_3_2_2_27_1","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 2017 USENIX Annual Technical Conference (USENIX ATC 17).181--193."}],"event":{"name":"IMC '20: ACM Internet Measurement Conference","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"],"location":"Virtual Event USA","acronym":"IMC '20"},"container-title":["Proceedings of the ACM Internet Measurement Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3419394.3423637","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3419394.3423637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T23:38:30Z","timestamp":1765841910000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3419394.3423637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,27]]},"references-count":27,"alternative-id":["10.1145\/3419394.3423637","10.1145\/3419394"],"URL":"https:\/\/doi.org\/10.1145\/3419394.3423637","relation":{},"subject":[],"published":{"date-parts":[[2020,10,27]]},"assertion":[{"value":"2020-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}