{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:03:44Z","timestamp":1764842624443,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T00:00:00Z","timestamp":1649203200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T00:00:00Z","timestamp":1649203200000},"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":[[2022,4,6]]},"DOI":"10.1109\/isqed54688.2022.9806197","type":"proceedings-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T19:46:20Z","timestamp":1656531980000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["An Automatic and Efficient BERT Pruning for Edge AI Systems"],"prefix":"10.1109","author":[{"given":"Shaoyi","family":"Huang","sequence":"first","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueying","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwu","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjia","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongkuan","family":"Xu","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mimi","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Texas at San Antonio"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.286"},{"key":"ref38","article-title":"Huggingface’s transformers: State-of-the-art natural language processing","author":"wolf","year":"2019","journal-title":"ArXiv abs\/1910 03771"},{"key":"ref33","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586152"},{"key":"ref31","article-title":"Sparse progressive distillation: Resolving overfitting under pretrain-and-finetune paradigm","author":"huang","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.188"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref36","article-title":"Automatically constructing a corpus of sentential paraphrases","author":"dolan","year":"0","journal-title":"Third International Workshop on Paraphrasing (IWP2005)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"ref34","first-page":"1","article-title":"Et: re-thinking self-attention for transformer models on gpus","author":"chen","year":"2021","journal-title":"Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174253"},{"key":"ref11","article-title":"What is the state of neural network pruning?","author":"blalock","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461740"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref15","article-title":"The lottery ticket hypothesis for pre-trained bert networks","author":"chen","year":"2020","journal-title":"arXiv preprint arXiv 2007 12869"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358028"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref4","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref27","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"arXiv preprint arXiv 1910 01108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1499"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref29","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","author":"wang","year":"2020","journal-title":"Advances in Neural Information Processing Sys-tems(NIPS)"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT (1)"},{"key":"ref8","first-page":"15 834","article-title":"The lottery ticket hypothesis for pre-trained bert networks","volume":"33","author":"chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12194"},{"key":"ref2","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref9","article-title":"Drawing early-bird tickets: Toward more efficient training of deep networks","author":"you","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.398"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP52443.2021.00021"},{"key":"ref23","article-title":"Reweighted proximal pruning for large-scale language representation","author":"guo","year":"2019","journal-title":"arXiv preprint arXiv 1909 11324"},{"key":"ref26","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"arXiv preprint arXiv 1803 03635"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461739"},{"key":"ref25","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 23rd International Symposium on Quality Electronic Design (ISQED)","start":{"date-parts":[[2022,4,6]]},"location":"Santa Clara, CA, USA","end":{"date-parts":[[2022,4,7]]}},"container-title":["2022 23rd International Symposium on Quality Electronic Design (ISQED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9806045\/9806137\/09806197.pdf?arnumber=9806197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:14:30Z","timestamp":1658780070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9806197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/isqed54688.2022.9806197","relation":{},"subject":[],"published":{"date-parts":[[2022,4,6]]}}}