{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:42:59Z","timestamp":1763192579186,"version":"3.45.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228254","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["A Neural Network-Based Pipeline Parallel Strategy Solver for Heterogeneous Environments"],"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":"Jinyu","family":"Guo","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":"Shuaihong","family":"Jiang","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":"Ruini","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"}],"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","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"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","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.066"},{"article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","volume-title":"International Conference on Learning Representations","author":"Lepikhin","key":"ref5"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref8","first-page":"6630","article-title":"Amp: Automatically finding model parallel strategies with heterogeneity awareness","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on {GPU} clusters","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Zhang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","year":"2019","author":"Shoeybi","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105710"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107648"},{"key":"ref20","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Mirhoseini"},{"article-title":"Auto-map: A dqn framework for exploring distributed execution plans for dnn workloads","year":"2020","author":"Wang","key":"ref21"},{"article-title":"Horovod: fast and easy distributed deep learning in tensorflow","year":"2018","author":"Sergeev","key":"ref22"},{"key":"ref23","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","volume":"26","author":"Ho","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref25"},{"year":"2024","key":"ref26","article-title":"Llama 3 model card"},{"article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","year":"2024","author":"Glm","key":"ref27"},{"article-title":"Qwen technical report","year":"2023","author":"Bai","key":"ref28"},{"article-title":"Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Jiang","key":"ref29"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228254.pdf?arnumber=11228254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:38:54Z","timestamp":1763192334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228254","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}