{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:06:41Z","timestamp":1782828401105,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CNS-2216746"],"award-info":[{"award-number":["CNS-2216746"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tmc.2023.3328287","type":"journal-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T19:38:26Z","timestamp":1698694706000},"page":"7012-7029","source":"Crossref","is-referenced-by-count":8,"title":["EdgeTran: Device-Aware Co-Search of Transformers for Efficient Inference on Mobile Edge Platforms"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9230-5877","authenticated-orcid":false,"given":"Shikhar","family":"Tuli","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1539-0369","authenticated-orcid":false,"given":"Niraj K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref3","article-title":"Using DeepSpeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model","author":"Smith","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13942"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref9","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.17"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.400"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3508396.3512869"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3529706.3529712"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3087349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3575798"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref18","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","volume-title":"Proc. Chin. Nat. Conf. Comput. Linguistics","author":"Zhuang"},{"key":"ref19","first-page":"12837","article-title":"ConvBERT: Improving BERT with span-based dynamic convolution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.250"},{"key":"ref22","first-page":"9782","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21311"},{"key":"ref24","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref26","first-page":"11711","article-title":"MCUNet: Tiny deep learning on IoT devices","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2914438"},{"key":"ref28","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref29","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2023.3283443"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref36","article-title":"Well-read students learn better: The impact of student initialization on knowledge distillation","author":"Turc","year":"1908"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/rsa.10073"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970081"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9449-2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref42","article-title":"Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Siems"},{"key":"ref43","first-page":"118","article-title":"Natural-parameter networks: A class of probabilistic neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref44","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref45","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sanh"},{"key":"ref46","first-page":"2376","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Xu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-6526(06)80008-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref52","article-title":"From RankNet to LambdaRank to LambdaMART: An overview","author":"Burges","year":"2010"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref54","article-title":"Apple unleashes M1","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref60","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"Proc. Int. Conf Learn. Representations","author":"Frantar"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD52597.2021.9531281"},{"key":"ref62","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref63","article-title":"Stanford Alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7755\/10521901\/10301516-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/10521901\/10301516.pdf?arnumber=10301516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T04:37:33Z","timestamp":1715143053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10301516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":57,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2023.3328287","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}