{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T21:05:19Z","timestamp":1772658319145,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010822","name":"Chengdu Science and Technology Bureau","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010822","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":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,9]]},"DOI":"10.1109\/dsaa65442.2025.11416804","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:48:52Z","timestamp":1772570932000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Efficient and Automatic 3D Parallelism Strategies Search via Contrastive Reinforcement Learning Pretrained Neural Networks"],"prefix":"10.1109","author":[{"given":"Jie","family":"Ou","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueming","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahong","family":"Qian","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Su","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhong","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0480"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref8","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.134"},{"key":"ref12","first-page":"6543","article-title":"Terapipe: Token-level pipeline parallelism for training large-scale language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref13","first-page":"2274","article-title":"Exploring hidden dimensions in accelerating convolutional neural networks","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473104"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref18","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Mirhoseini"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00109"},{"key":"ref20","article-title":"Auto-map: A dqn framework for exploring distributed execution plans for dnn workloads","author":"Wang","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2879-6_5"},{"key":"ref23","first-page":"1","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Narayanan"},{"key":"ref24","first-page":"24829","article-title":"Piper: Multidimensional planner for dnn parallelization","volume":"34","author":"Tarnawski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"559","article-title":"Alpa: Automating inter-and {IntraOperator} parallelism for distributed deep learning","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng"},{"key":"ref26","article-title":"Attention, learn to solve routing problems!","volume-title":"International Conference on Learning Representations","author":"Kool"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref30","first-page":"14745","article-title":"Transgan: Two pure transformers can make one strong gan, and that can scale up","volume":"34","author":"Jiang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)","location":"Birmingham, United Kingdom","start":{"date-parts":[[2025,10,9]]},"end":{"date-parts":[[2025,10,12]]}},"container-title":["2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11247920\/11247921\/11416804.pdf?arnumber=11416804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:46:48Z","timestamp":1772657208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11416804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/dsaa65442.2025.11416804","relation":{},"subject":[],"published":{"date-parts":[[2025,10,9]]}}}