{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:47:56Z","timestamp":1761324476650,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892797","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models"],"prefix":"10.1109","author":[{"given":"Amrit","family":"Nagarajan","sequence":"first","affiliation":[{"name":"School of ECE, Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanchari","family":"Sen","sequence":"additional","affiliation":[{"name":"School of ECE, Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob R.","family":"Stevens","sequence":"additional","affiliation":[{"name":"School of ECE, Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Raghunathan","sequence":"additional","affiliation":[{"name":"School of ECE, Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Train big, then compress: Rethinking model size for efficient training and inference of transformers","author":"li","year":"0","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.510"},{"key":"ref12","article-title":"Are sixteen heads really better than one?","author":"michel","year":"0","journal-title":"NeurIPS 2019"},{"key":"ref13","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"0","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.259"},{"journal-title":"Language Models are Unsupervised Multitask Learners","year":"2019","author":"radford","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"journal-title":"Poor man's bert Smaller and faster transformer models","year":"2020","author":"sajjad","key":"ref17"},{"key":"ref18","article-title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref4","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"0","journal-title":"ICLRE"},{"key":"ref3","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"dodge","year":"2020","journal-title":"CoRR"},{"key":"ref6","article-title":"Dynabert: Dynamic BERT with adaptive width and depth","author":"hou","year":"0","journal-title":"NeurIPS 2020"},{"key":"ref5","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"0","journal-title":"ICLRE"},{"key":"ref8","article-title":"Tinybert: Distilling BERT for natural language understanding","author":"jiao","year":"2019","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref2","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"NAACL HLT 2019"},{"key":"ref9","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"ICLRE"},{"key":"ref1","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref22","article-title":"Huggingface's transformers: State-of-the-art natural language processing","author":"wolf","year":"2019","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"ref23","article-title":"Lite transformer with long-short range attention","author":"wu","year":"0","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref25","article-title":"Good subnetworks provably exist: Pruning via greedy forward selection","author":"ye","year":"0","journal-title":"ICML"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892797.pdf?arnumber=9892797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:56:45Z","timestamp":1667516205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892797","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}