{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:07:53Z","timestamp":1784099273297,"version":"3.55.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/icc59461.2026.11588116","type":"proceedings-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:38:09Z","timestamp":1784057889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["ScaleDL: Towards Scalable and Efficient Runtime Prediction for Distributed Deep Learning Workloads"],"prefix":"10.1109","author":[{"given":"Xiaokai","family":"Wang","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3568022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"T","year":"2023"},{"key":"ref4","first-page":"503","article-title":"Habitat: A Runtime-Based computational performance predictor for deep neural network training","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Yu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3729215"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599453"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3476390"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621424"},{"key":"ref9","article-title":"Paleo: A performance model for deep neural networks","volume-title":"International Conference on Learning Representations","author":"Qi"},{"key":"ref10","first-page":"380","article-title":"Path forward beyond simulators: Fast and accurate gpu execution time prediction for dnn workloads","volume-title":"Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/793"},{"issue":"1","key":"ref15","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref18","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref19","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICLR.","author":"Touvron","year":"2021"},{"key":"ref20","article-title":"Predicting llm inference latency: A roofline-driven ml method","volume-title":"Annual Conference on Neural Information Processing Systems","author":"Imai"},{"key":"ref21","article-title":"Learning to represent programs with graphs","author":"Allamanis","year":"2017"}],"event":{"name":"ICC 2026 - IEEE International Conference on Communications","location":"Glasgow, United Kingdom","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["ICC 2026 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11586754\/11586037\/11588116.pdf?arnumber=11588116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:27:10Z","timestamp":1784096830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11588116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icc59461.2026.11588116","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}