{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:57:09Z","timestamp":1781024229736,"version":"3.54.1"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.asoc.2026.115426","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:10:40Z","timestamp":1778760640000},"page":"115426","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["An auto-parallel training method for deep learning models with extracting model structural features"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2026-417X","authenticated-orcid":false,"given":"Yan","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyu","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianggan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6861-9684","authenticated-orcid":false,"given":"Honghao","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115426_bib0005","series-title":"2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)","first-page":"498","article-title":"Scalable distributed DNN training using tensorflow and CUDA-aware MPI: characterization, designs, and performance evaluation","author":"Awan","year":"2019"},{"key":"10.1016\/j.asoc.2026.115426_bib0010","author":"\u0160tef\u00e1nik"},{"key":"10.1016\/j.asoc.2026.115426_bib0015","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1038\/s42256-022-00604-2","article-title":"Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks","volume":"5","author":"Luo","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.asoc.2026.115426_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119493","article-title":"Shortlisting machine learning-based stock trading recommendations using candlestick pattern recognition","volume":"216","author":"Cagliero","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.115426_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7153","article-title":"End-to-end model-free reinforcement learning for urban driving using implicit affordances","author":"Toromanoff","year":"2020"},{"key":"10.1016\/j.asoc.2026.115426_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmb.2021.167208","article-title":"AlphaFold and implications for intrinsically disordered proteins","volume":"433","author":"Ruff","year":"2021","journal-title":"J. Mol. Biol."},{"key":"10.1016\/j.asoc.2026.115426_bib0035","doi-asserted-by":"crossref","first-page":"17","DOI":"10.3354\/esep00195","article-title":"Plagiarism in the age of massive generative pre-trained transformers (GPT-3)","volume":"21","author":"Dehouche","year":"2021","journal-title":"Ethics in Science and Environmental Politics"},{"key":"10.1016\/j.asoc.2026.115426_bib0040","doi-asserted-by":"crossref","first-page":"42735","DOI":"10.1007\/s11042-023-16676-0","article-title":"Automated schizophrenia detection model using blood sample scattergram images and local binary pattern","volume":"83","author":"Tasci","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.asoc.2026.115426_bib0045","series-title":"Papers on Twenty-Five Years of Electronic Design Automation","first-page":"241","article-title":"A linear-time heuristic for improving network partitions","author":"Fiduccia","year":"1988"},{"key":"10.1016\/j.asoc.2026.115426_bib0050","series-title":"Proceedings of the 21st International Middleware Conference","first-page":"105","article-title":"Fast training of deep learning models over multiple GPUs","author":"Yi","year":"2020"},{"key":"10.1016\/j.asoc.2026.115426_bib0055","series-title":"Proceedings of the 11th ACM Symposium on Cloud Computing","first-page":"416","article-title":"Baechi: fast device placement of machine learning graphs","author":"Jeon","year":"2020"},{"key":"10.1016\/j.asoc.2026.115426_bib0060","series-title":"International Conference on Machine Learning","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"Mirhoseini","year":"2017"},{"key":"10.1016\/j.asoc.2026.115426_bib0065","series-title":"International Conference on Learning Representations","article-title":"A hierarchical model for device placement","author":"Mirhoseini","year":"2018"},{"key":"10.1016\/j.asoc.2026.115426_bib0070","series-title":"International Conference on Machine Learning","first-page":"1676","article-title":"Spotlight: optimizing device placement for training deep neural networks","author":"Gao","year":"2018"},{"key":"10.1016\/j.asoc.2026.115426_bib0075","series-title":"Experimental analysis of the dual recursive bipartitioning algorithm for static mapping","author":"cois Pellegrini","year":"1996"},{"key":"10.1016\/j.asoc.2026.115426_bib0080","series-title":"ICML","first-page":"2279","article-title":"Exploring hidden dimensions in parallelizing convolutional neural networks","author":"Jia","year":"2018"},{"key":"10.1016\/j.asoc.2026.115426_bib0085","series-title":"Proceedings of the Thirteenth EuroSys Conference","first-page":"1","article-title":"Optimus: an efficient dynamic resource scheduler for deep learning clusters","author":"Peng","year":"2018"},{"key":"10.1016\/j.asoc.2026.115426_bib0090","first-page":"906","article-title":"Autosync: learning to synchronize for data-parallel distributed deep learning","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115426_bib0095","series-title":"Proceedings of the Fourteenth EuroSys Conference 2019","first-page":"1","article-title":"Parallax: sparsity-aware data parallel training of deep neural networks","author":"Kim","year":"2019"},{"key":"10.1016\/j.asoc.2026.115426_bib0100","author":"Frazier"},{"key":"10.1016\/j.asoc.2026.115426_bib0105","article-title":"Post: device placement with cross-entropy minimization and proximal policy optimization","volume":"31","author":"Gao","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115426_bib0110","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"Jia","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115426_bib0115","author":"Addanki"},{"key":"10.1016\/j.asoc.2026.115426_bib0120","author":"Paliwal"},{"key":"10.1016\/j.asoc.2026.115426_bib0125","author":"Wang"},{"key":"10.1016\/j.asoc.2026.115426_bib0130","doi-asserted-by":"crossref","first-page":"108","DOI":"10.3390\/a15040108","article-title":"Trinity: neural network adaptive distributed parallel training method based on reinforcement learning","volume":"15","author":"Zeng","year":"2022","journal-title":"Algorithms"},{"key":"10.1016\/j.asoc.2026.115426_bib0135","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0304-3975(81)90081-5","article-title":"Non deterministic polynomial optimization problems and their approximations","volume":"15","author":"Paz","year":"1981","journal-title":"Theor. Comput. Sci."},{"key":"10.1016\/j.asoc.2026.115426_bib0140","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1007\/s42514-022-00098-9","article-title":"MP-DPS: adaptive distributed training for deep learning based on node merging and path prediction","volume":"5","author":"Zeng","year":"2023","journal-title":"CCF Trans. High Perform. Comput."},{"key":"10.1016\/j.asoc.2026.115426_bib0145","doi-asserted-by":"crossref","first-page":"4788","DOI":"10.3390\/math10244788","article-title":"Adaptive distributed parallel training method for a deep learning model based on dynamic critical paths of DAG","volume":"10","author":"Zeng","year":"2022","journal-title":"Mathematics"},{"key":"10.1016\/j.asoc.2026.115426_bib0150","series-title":"2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys)","first-page":"1299","article-title":"Aware: adaptive distributed training with computation, communication and position awareness for deep learning model","author":"Zeng","year":"2022"},{"key":"10.1016\/j.asoc.2026.115426_bib0155","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115426_bib0160","author":"Mnih"},{"key":"10.1016\/j.asoc.2026.115426_bib0165","author":"Wang"},{"key":"10.1016\/j.asoc.2026.115426_bib0170","author":"Zheng"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008744?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008744?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:59:42Z","timestamp":1781020782000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626008744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":34,"alternative-id":["S1568494626008744"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115426","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An auto-parallel training method for deep learning models with extracting model structural features","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115426","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115426"}}