{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:27:59Z","timestamp":1757543279260,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s13042-023-01903-9","type":"journal-article","created":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T07:02:21Z","timestamp":1687935741000},"page":"207-226","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["2D-THA-ADMM: communication efficient distributed ADMM algorithm framework based on two-dimensional torus hierarchical AllReduce"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5260-3458","authenticated-orcid":false,"given":"Guozheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongmei","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunlu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"1903_CR1","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.jpdc.2021.05.012","volume":"156","author":"R Gu","year":"2021","unstructured":"Gu R, Qi Y, Wu T, Wang Z, Xu X, Yuan C, Huang Y (2021) Sparkdq: efficient generic big data quality management on distributed data-parallel computation. J Parall Distrib Comput 156:132\u2013147","journal-title":"J Parall Distrib Comput"},{"key":"1903_CR2","doi-asserted-by":"crossref","unstructured":"Nagrecha K (2021) Model-parallel model selection for deep learning systems. In: Proceedings of the 2021 international conference on management of data, pp 2929\u20132931","DOI":"10.1145\/3448016.3450571"},{"key":"1903_CR3","doi-asserted-by":"publisher","first-page":"4733","DOI":"10.1109\/TIFS.2021.3113768","volume":"16","author":"F Shang","year":"2021","unstructured":"Shang F, Xu T, Liu Y, Liu H, Shen L, Gong M (2021) Differentially private ADMM algorithms for machine learning. IEEE Trans Inf Forens Secur 16:4733\u20134745","journal-title":"IEEE Trans Inf Forens Secur"},{"key":"1903_CR4","volume-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","author":"S Boyd","year":"2011","unstructured":"Boyd S, Parikh N, Chu E (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Now Publishers Inc, Norwell"},{"key":"1903_CR5","unstructured":"Yang Y, Guan X, Jia Q.-S, Yu L, Xu B, Spanos CJ (2022) A survey of ADMM variants for distributed optimization: problems, algorithms and features. arXiv preprint arXiv:2208.03700"},{"issue":"1","key":"1903_CR6","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TCOMM.2020.3026398","volume":"69","author":"A Elgabli","year":"2020","unstructured":"Elgabli A, Park J, Bedi AS, Issaid CB, Bennis M, Aggarwal V (2020) Q-GADMM: quantized group ADMM for communication efficient decentralized machine learning. IEEE Trans Commun 69(1):164\u2013181","journal-title":"IEEE Trans Commun"},{"key":"1903_CR7","doi-asserted-by":"publisher","first-page":"8111","DOI":"10.1007\/s11227-020-03590-7","volume":"77","author":"D Wang","year":"2021","unstructured":"Wang D, Lei Y, Xie J, Wang G (2021) HSAC-ALADMM: an asynchronous lazy ADMM algorithm based on hierarchical sparse allreduce communication. J Supercomput 77:8111\u20138134","journal-title":"J Supercomput"},{"key":"1903_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109051","volume":"124","author":"Z Liu","year":"2022","unstructured":"Liu Z, Xu Y (2022) Multi-task nonparallel support vector machine for classification. Appl Soft Comput 124:109051","journal-title":"Appl Soft Comput"},{"key":"1903_CR9","doi-asserted-by":"crossref","unstructured":"Zhou S, Li GY (2023) Federated learning via inexact ADMM. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2023.3243080"},{"issue":"8","key":"1903_CR10","doi-asserted-by":"publisher","first-page":"3290","DOI":"10.1109\/TNNLS.2021.3051638","volume":"33","author":"Y Liu","year":"2021","unstructured":"Liu Y, Wu G, Tian Z, Ling Q (2021) Dqc-admm: decentralized dynamic admm with quantized and censored communications\u2019\u2019. IEEE Trans Neural Netw Learn Syst 33(8):3290\u20133304","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"1903_CR11","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1109\/TNET.2021.3117042","volume":"30","author":"S Wang","year":"2021","unstructured":"Wang S, Geng J, Li D (2021) Impact of synchronization topology on dml performance: both logical topology and physical topology. IEEE\/ACM Trans Netw 30(2):572\u2013585","journal-title":"IEEE\/ACM Trans Netw"},{"key":"1903_CR12","doi-asserted-by":"crossref","unstructured":"Sun DL, Fevotte C (2014) Alternating direction method of multipliers for non-negative matrix factorization with the beta-divergence. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp\u00a06201\u20136205","DOI":"10.1109\/ICASSP.2014.6854796"},{"issue":"3","key":"1903_CR13","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/MNET.011.2000530","volume":"35","author":"S Shi","year":"2020","unstructured":"Shi S, Tang Z, Chu X, Liu C, Wang W, Li B (2020) A quantitative survey of communication optimizations in distributed deep learning. IEEE Netw 35(3):230\u2013237","journal-title":"IEEE Netw"},{"issue":"1","key":"1903_CR14","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R Thakur","year":"2005","unstructured":"Thakur R, Rabenseifner R, Gropp W (2005) Optimization of collective communication operations in mpich. Int J High Perform Comput Appl 19(1):49\u201366","journal-title":"Int J High Perform Comput Appl"},{"issue":"01","key":"1903_CR15","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1142\/S0129626407002880","volume":"17","author":"RL Graham","year":"2007","unstructured":"Graham RL, Barrett BW, Shipman GM, Woodall TS, Bosilca G (2007) Open mpi: a high performance, flexible implementation of mpi point-to-point communications. Parall Process Lett 17(01):79\u201388","journal-title":"Parall Process Lett"},{"issue":"2","key":"1903_CR16","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.jpdc.2008.09.002","volume":"69","author":"P Patarasuk","year":"2009","unstructured":"Patarasuk P, Yuan X (2009) Bandwidth optimal all-reduce algorithms for clusters of workstations. J Parall Distrib Comput 69(2):117\u2013124","journal-title":"J Parall Distrib Comput"},{"key":"1903_CR17","unstructured":"Research B (2017) \u201cbaidu-allreduce.\u201d [Online]. https:\/\/github.com\/baidu-research\/baidu-allreduce"},{"key":"1903_CR18","doi-asserted-by":"crossref","unstructured":"Lee J, Hwang I, Shah S, Cho M (2020) Flexreduce: Flexible all-reduce for distributed deep learning on asymmetric network topology. In: 2020 57th ACM\/IEEE design automation conference (DAC). IEEE, pp\u00a01\u20136","DOI":"10.1109\/DAC18072.2020.9218538"},{"key":"1903_CR19","unstructured":"Sanghoon J, Son H, Kim J (2023) Logical\/physical topology-aware collective communication in deep learning training. In: 2023 IEEE International symposium on high-performance computer architecture (HPCA). IEEE, pp\u00a056\u201368"},{"issue":"11","key":"1903_CR20","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/JPROC.2020.3022687","volume":"108","author":"G Fran\u00e7a","year":"2020","unstructured":"Fran\u00e7a G, Bento J (2020) Distributed optimization, averaging via admm, and network topology. Proc IEEE 108(11):1939\u20131952","journal-title":"Proc IEEE"},{"key":"1903_CR21","doi-asserted-by":"crossref","unstructured":"Tavara S, Schliep A (2018) Effect of network topology on the performance of admm-based svms. In: 2018 30th international symposium on computer architecture and high performance computing (SBAC-PAD). IEEE, pp\u00a0388\u2013393","DOI":"10.1109\/CAHPC.2018.8645857"},{"issue":"12","key":"1903_CR22","doi-asserted-by":"publisher","first-page":"2737","DOI":"10.1007\/s00607-021-00968-0","volume":"103","author":"D Wang","year":"2021","unstructured":"Wang D, Lei Y, Zhou J (2021) Hybrid mpi\/openmp parallel asynchronous distributed alternating direction method of multipliers. Computing 103(12):2737\u20132762","journal-title":"Computing"},{"key":"1903_CR23","doi-asserted-by":"crossref","unstructured":"Xie J, Lei Y (2019) Admmlib: a library of communication-efficient ad-admm for distributed machine learning. In: IFIP international conference on network and parallel computing. Springer, pp 322\u2013326","DOI":"10.1007\/978-3-030-30709-7_27"},{"key":"1903_CR24","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu W, Wang B, Wang G, Xi Y, Liu H, Wang S, Zhang J (2022)Asynchronous decomposition method for the coordinated operation of virtual power plants. IEEE Trans Power Syst","DOI":"10.1109\/TPWRS.2022.3162329"},{"key":"1903_CR25","doi-asserted-by":"crossref","unstructured":"Li M, Andersen DG, Smola AJ, Yu K (2014) Communication efficient distributed machine learning with the parameter server. Adv Neural Inf Process Syst 27","DOI":"10.1145\/2640087.2644155"},{"key":"1903_CR26","doi-asserted-by":"crossref","unstructured":"Zhang Z, Yang S, Xu W, Di K (2022) Privacy-preserving distributed admm with event-triggered communication. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2022.3192346"},{"key":"1903_CR27","doi-asserted-by":"crossref","unstructured":"Huang J, Majumder P, Kim S, Muzahid A, Yum KH, Kim EJ (2021) \u201cCommunication algorithm-architecture co-design for distributed deep learning. In: 2021 ACM\/IEEE 48th annual international symposium on computer architecture (ISCA). IEEE, pp 181\u2013194","DOI":"10.1109\/ISCA52012.2021.00023"},{"key":"1903_CR28","unstructured":"Mikami H, Suganuma H, Tanaka Y, Kageyama Y et al (2018) Massively distributed sgd: Imagenet\/resnet-50 training in a flash. arXiv preprint arXiv:1811.05233"},{"key":"1903_CR29","first-page":"241","volume":"1","author":"M Cho","year":"2019","unstructured":"Cho M, Finkler U, Kung D, Hunter H (2019) Blueconnect: decomposing all-reduce for deep learning on heterogeneous network hierarchy. Proc Mach Learn Syst 1:241\u2013251","journal-title":"Proc Mach Learn Syst"},{"key":"1903_CR30","first-page":"172","volume":"2","author":"G Wang","year":"2020","unstructured":"Wang G, Venkataraman S, Phanishayee A, Devanur N, Thelin J, Stoica I (2020) Blink: fast and generic collectives for distributed ml. Proc Mach Learn Syst 2:172\u2013186","journal-title":"Proc Mach Learn Syst"},{"key":"1903_CR31","doi-asserted-by":"crossref","unstructured":"Kielmann T, Hofman RF, Bal HE, Plaat A, Bhoedjang RA (1999) Magpie: Mpi\u2019s collective communication operations for clustered wide area systems. In: Proceedings of the seventh ACM SIGPLAN symposium on Principles and practice of parallel programming, pp\u00a0131\u2013140","DOI":"10.1145\/329366.301116"},{"key":"1903_CR32","doi-asserted-by":"crossref","unstructured":"Zhu H, Goodell D, Gropp W, Thakur R (2009) Hierarchical collectives in mpich2. In: European parallel virtual machine\/message passing interface users\u2019 group meeting. Springer, pp\u00a0325\u2013326","DOI":"10.1007\/978-3-642-03770-2_41"},{"key":"1903_CR33","doi-asserted-by":"crossref","unstructured":"Bayatpour M, Chakraborty S, Subramoni H, Lu X, Panda DK (2017) Scalable reduction collectives with data partitioning-based multi-leader design. In: Proceedings of the international conference for high performance computing, networking, storage and analysis, pp 1\u201311","DOI":"10.1145\/3126908.3126954"},{"key":"1903_CR34","unstructured":"Jia X, Song S, He W, Wang Y, Rong H, Zhou F, Xie L, Guo Z, Yang Y, Yu L et al (2018) Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes. arXiv preprint arXiv:1807.11205"},{"key":"1903_CR35","first-page":"18195","volume":"34","author":"M Ryabinin","year":"2021","unstructured":"Ryabinin M, Gorbunov E, Plokhotnyuk V, Pekhimenko G (2021) Moshpit sgd: communication-efficient decentralized training on heterogeneous unreliable devices. Adv Neural Inf Process Syst 34:18195\u201318211","journal-title":"Adv Neural Inf Process Syst"},{"key":"1903_CR36","doi-asserted-by":"crossref","unstructured":"Lin CJ, Weng RC, Keerthi SS (2008) Trust region newton method for large-scale logistic regression. J Mach Learn Res 9(4)","DOI":"10.1145\/1273496.1273567"},{"key":"1903_CR37","doi-asserted-by":"crossref","unstructured":"Mamidala AR, Liu J, Panda DK (2004) Efficient barrier and allreduce on infiniband clusters using multicast and adaptive algorithms. In: 2004 IEEE international conference on cluster computing (IEEE Cat. No. 04EX935). IEEE, pp 135\u2013144","DOI":"10.1109\/CLUSTR.2004.1392611"},{"key":"1903_CR38","unstructured":"Ho Q, Cipar J, Cui H, Lee S, Kim JK, Gibbons PB, Gibson GA, Ganger G, Xing EP (2013) More effective distributed ml via a stale synchronous parallel parameter server. In: Advances in neural information processing systems, pp 1223\u20131231"},{"key":"1903_CR39","unstructured":"Zhang R, Kwok J (2014) Asynchronous distributed admm for consensus optimization. In: International conference on machine learning. PMLR, pp\u00a01701\u20131709"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-023-01903-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-023-01903-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-023-01903-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T16:21:08Z","timestamp":1705076468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-023-01903-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1903"],"URL":"https:\/\/doi.org\/10.1007\/s13042-023-01903-9","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2023,6,28]]},"assertion":[{"value":"27 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}