{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T13:50:51Z","timestamp":1770990651800,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T00:00:00Z","timestamp":1648166400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T00:00:00Z","timestamp":1648166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172442"],"award-info":[{"award-number":["62172442"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172451"],"award-info":[{"award-number":["62172451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2020JJ5775"],"award-info":[{"award-number":["2020JJ5775"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11227-022-04422-6","type":"journal-article","created":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T17:29:39Z","timestamp":1648229379000},"page":"13865-13892","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DOSP: an optimal synchronization of parameter server for distributed machine learning"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8084-5203","authenticated-orcid":false,"given":"Meiguang","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Dongbang","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Liu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yeming","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Zhigang","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,25]]},"reference":[{"issue":"11","key":"4422_CR1","first-page":"2749","volume":"26","author":"X He","year":"2015","unstructured":"He X, Guo M, Zhang M (2015) Preface to the big data time machine learning research special issue. J Softw 26(11):2749\u20132751","journal-title":"J Softw"},{"issue":"7553","key":"4422_CR2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"4422_CR3","unstructured":"Li M, Andersen DG, Park JW, et al (2014) Scaling distributed machine learning with the parameter server. In: Proceedings of 11th Symposium on Operating Systems Design and Implementation (OSDI), pp 583\u2013598. USENIX, Broomfield, CO, USA"},{"key":"4422_CR4","unstructured":"Chilimbi TM, Suzue Y, Apacible J, Kalyanaraman K (2014) Project adam: building an efficient and scalable deep learning training system. In: Proceedings of 11th Symposium on Operating Systems Design and Implementation (OSDI), pp 571\u2013582. USENIX, Broomfield, CO, USA"},{"key":"4422_CR5","unstructured":"Abadi M, Barham P, Chen J, et al (2016) Tensorflow: a system for large-scale machine learning. In: Proceedings of 12th Symposium on Operating Systems Design and Implementation (OSDI), pp 265\u2013283. USENIX, Savannah, GA, USA"},{"issue":"1\u20132","key":"4422_CR6","doi-asserted-by":"publisher","first-page":"703","DOI":"10.14778\/1920841.1920931","volume":"3","author":"AJ Smola","year":"2010","unstructured":"Smola AJ, Narayanamurthy SM (2010) An architecture for parallel topic models. Proc VLDB Endow 3(1\u20132):703\u2013710","journal-title":"Proc VLDB Endow"},{"key":"4422_CR7","doi-asserted-by":"crossref","unstructured":"Harlap A, Cui H, Dai W, et al (2016) Addressing the straggler problem for iterative convergent parallel ml. In: Proceedings of the 7th ACM Symposium on Cloud Computing (SoCC), pp 98\u2013111. ACM, Santa Clara, CA, USA","DOI":"10.1145\/2987550.2987554"},{"key":"4422_CR8","doi-asserted-by":"crossref","unstructured":"Acar UA, Chargu\u00e9raud A, Rainey M (2013) Scheduling parallel programs by work stealing with private deques. In: Proceedings of ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), pp 219\u2013228. ACM, Shenzhen, China","DOI":"10.1145\/2517327.2442538"},{"key":"4422_CR9","doi-asserted-by":"crossref","unstructured":"Chen C, Weng Q, Wang W, et al (2018) Fast distributed deep learning via worker-adaptive batch sizing. In: Proceedings of the ACM Symposium on Cloud Computing (SoCC), p 521. ACM, Carlsbad, CA, USA","DOI":"10.1145\/3267809.3275463"},{"key":"4422_CR10","unstructured":"Dean J, Corrado G, Monga R, et al (2012) Large scale distributed deep networks. In: Proceedings of 26th Annual Conference on Neural Information Processing Systems (NIPS), pp 1232\u20131240. IEEE, Lake Tahoe, Nevada, United States"},{"key":"4422_CR11","unstructured":"Recht B, R\u00e9 C, Wright SJ, et al (2011) F. N.: Hogwild: a lock-free approach to parallelizing stochastic gradient descent. In: Proceedings of 25th Annual Conference on Neural Information Processing Systems (NIPS), pp 693\u2013701. IEEE, Granada, Spain"},{"key":"4422_CR12","doi-asserted-by":"crossref","unstructured":"Dai W, Kumar A, Wei J, et al (2015) High-performance distributed ML at scale through parameter server consistency models. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), pp 79\u201387. AAAI Press, Austin, Texas, USA","DOI":"10.1609\/aaai.v29i1.9195"},{"key":"4422_CR13","doi-asserted-by":"crossref","unstructured":"Li Y, Wan H, Jiang B, Long X (2016) More effective synchronization scheme in ml using stale parameters. In: Proceedings of 18th IEEE International Conference on High Performance Computing (HPCC), pp 757\u2013764. IEEE, Sydney, Australia","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0110"},{"key":"4422_CR14","doi-asserted-by":"crossref","unstructured":"Wei J, Dai W, Qiao A, et al (2015) Managed communication and consistency for fast data-parallel iterative analytics. In: Proceedings of the 6th ACM Symposium on Cloud Computing (SoCC), pp 381\u2013394. ACM, Kohala Coast, Hawaii, USA","DOI":"10.1145\/2806777.2806778"},{"key":"4422_CR15","doi-asserted-by":"crossref","unstructured":"Lu H, Wang K (2021) Distributed machine learning based mitigating straggler in big data environment. In: Proceedings of International Conference on Communications (ICC), pp 1\u20136. IEEE, Montreal, QC, Canada","DOI":"10.1109\/ICC42927.2021.9500531"},{"key":"4422_CR16","unstructured":"Ho Q, Cipar J, Cui H, et al (2013) More effective distributed ML via a stale synchronous parallel parameter server. In: Proceedings of 27th Annual Conference on Neural Information Processing Systems 2013 (NIPS), pp 1223\u20131231. IEEE, Lake Tahoe, Nevada, United States"},{"key":"4422_CR17","unstructured":"Zhang H, Hu Z, Wei J, et al (2015) Poseidon: a system architecture for efficient gpu-based deep learning on multiple machines. CoRR abs\/1512.06216"},{"issue":"1","key":"4422_CR18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TC.2020.2974461","volume":"70","author":"Q Zhou","year":"2021","unstructured":"Zhou Q, Guo S, Lu H et al (2021) Falcon: addressing stragglers in heterogeneous parameter server via multiple parallelism. IEEE Trans Comput 70(1):139\u2013155","journal-title":"IEEE Trans Comput"},{"key":"4422_CR19","unstructured":"Cipar J, Ho Q, Kim JK, et al (2013) Solving the straggler problem with bounded staleness. In: Proceedings of 14th Workshop on Hot Topics in Operating Systems (HotOS). USENIX, Santa Ana Pueblo, New Mexico, USA"},{"key":"4422_CR20","doi-asserted-by":"crossref","unstructured":"Jiang J, Cui B, Zhang C, Yu, L (2017) Heterogeneity-aware distributed parameter servers. In: Proceedings of the 2017 ACM International Conference on Management of Data (SIGMOD), pp 463\u2013478. ACM, Chicago, IL, USA","DOI":"10.1145\/3035918.3035933"},{"key":"4422_CR21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.jpdc.2019.10.004","volume":"137","author":"KS Chahal","year":"2020","unstructured":"Chahal KS, Grover MS, Dey K, Shah RR (2020) A hitchhiker\u2019s guide on distributed training of deep neural networks. J Parallel Distrib Comput 137:65\u201376","journal-title":"J Parallel Distrib Comput"},{"issue":"1","key":"4422_CR22","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) Mapreduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113","journal-title":"Commun ACM"},{"key":"4422_CR23","unstructured":"Zaharia M, Chowdhury M, Das T, et al (2012) Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI), pp 15\u201328. USENIX, San Jose, CA, USA"},{"key":"4422_CR24","doi-asserted-by":"crossref","unstructured":"Xin RS, Gonzalez JE, Franklin MJ, Stoica I (2013) Graphx: a resilient distributed graph system on spark. In: Proceedings of the 1th International Workshop on Graph Data Management Experiences and Systems (GRADES), pp 1\u20136. CWI\/ACM, New York, NY, USA","DOI":"10.1145\/2484425.2484427"},{"key":"4422_CR25","doi-asserted-by":"crossref","unstructured":"Zhang R, Shen G, Gong L, Guo C (2020) Dsana: a distributed machine learning acceleration solution based on dynamic scheduling and network acceleration. In: Proceedings of 22nd IEEE International Conference on High Performance Computing and Communications; 18th IEEE International Conference on Smart City; 6th IEEE International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp 302\u2013311. IEEE, Yanuca Island, Cuvu, Fiji","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00037"},{"key":"4422_CR26","doi-asserted-by":"crossref","unstructured":"Yu H, Zhu Z, Chen X, et al (2019) Accelerating distributed training in heterogeneous clusters via a straggler-aware parameter server. In: Proceedings of 21st IEEE International Conference on High Performance Computing and Communications; 17th IEEE International Conference on Smart City; 5th IEEE International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp 200\u2013207. IEEE, Zhangjiajie, China","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00042"},{"issue":"11","key":"4422_CR27","first-page":"2396","volume":"56","author":"Z Ji","year":"2019","unstructured":"Ji Z, Zhang X, Fu Z et al (2019) Dbs-sgd algorithm based on performance awareness in distributed deep learning framework. J Comput Res Develop 56(11):2396\u20132409","journal-title":"J Comput Res Develop"},{"issue":"8","key":"4422_CR28","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1109\/JSAC.2021.3087272","volume":"39","author":"H Wang","year":"2021","unstructured":"Wang H, Qu Z, Guo S et al (2021) Losp: overlap synchronization parallel with local compensation for fast distributed training. IEEE J Sel Areas Commun 39(8):2541\u20132557","journal-title":"IEEE J Sel Areas Commun"},{"key":"4422_CR29","doi-asserted-by":"crossref","unstructured":"Zhang C, Tian H, Wang W, Yan F (2018) Stay fresh: speculative synchronization for fast distributed machine learning. In: Proceedings of IEEE 38th International Conference on Distributed Computing Systems (ICDCS), pp 99\u2013109. IEEE, Vienna, Austria","DOI":"10.1109\/ICDCS.2018.00020"},{"key":"4422_CR30","unstructured":"Zhang W, Gupta S, Lian X, Liu J (2016) Staleness-aware async-sgd for distributed deep learning. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), pp 2350\u20132356. IJCAI\/AAAI Press, New York, NY, USA"},{"key":"4422_CR31","doi-asserted-by":"crossref","unstructured":"Zhao X, An A, Liu J, Chen BX (2019) Dynamic stale synchronous parallel distributed training for deep learning. In: Proceedings of 39th IEEE International Conference on Distributed Computing Systems (ICDCS), pp 1507\u20131517. IEEE, Dallas, TX, USA","DOI":"10.1109\/ICDCS.2019.00150"},{"issue":"3","key":"4422_CR32","first-page":"182","volume":"3","author":"E Diaconescu","year":"2008","unstructured":"Diaconescu E (2008) The use of narx neural networks to predict chaotic time series. WSEAS Trans Comput Res 3(3):182\u2013191","journal-title":"WSEAS Trans Comput Res"},{"key":"4422_CR33","unstructured":"http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"4422_CR34","doi-asserted-by":"crossref","unstructured":"Yang P, Xu, L (2011) A survey of deployment information of delay-based tcp congestion avoidance algorithm for transmitting multimedia data. In: Workshops Proceedings of the Global Communications Conference (GLOBECOM), pp 18\u201323. IEEE, Houston, Texas, USA","DOI":"10.1109\/GLOCOMW.2011.6162434"},{"key":"4422_CR35","unstructured":"https:\/\/www.grpc.io\/docs\/guides\/concepts\/"},{"key":"4422_CR36","unstructured":"https:\/\/keras.io\/"},{"key":"4422_CR37","unstructured":"https:\/\/psutil.readthedocs.io\/en\/latest\/"},{"issue":"4","key":"4422_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2827872","volume":"5","author":"FM Harper","year":"2016","unstructured":"Harper FM, Konstan JA (2016) The movielens datasets: history and context. ACM Trans Interact Intell Syst 5(4):1\u201319","journal-title":"ACM Trans Interact Intell Syst"},{"key":"4422_CR39","unstructured":"http:\/\/yann.lecun.com\/exdb\/MNIST\/"},{"key":"4422_CR40","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun, J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp 1026\u20131034. IEEE, Santiago, Chile","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04422-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-022-04422-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-022-04422-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T16:35:29Z","timestamp":1658162129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-022-04422-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,25]]},"references-count":40,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["4422"],"URL":"https:\/\/doi.org\/10.1007\/s11227-022-04422-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,25]]},"assertion":[{"value":"1 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}