{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:28:19Z","timestamp":1730266099681,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191515","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Flexible BERT with Width- and Depth-dynamic Inference"],"prefix":"10.1109","author":[{"given":"Ting","family":"Hu","sequence":"first","affiliation":[{"name":"Hasso Plattner Institute University of Potsdam,Potsdam,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Meinel","sequence":"additional","affiliation":[{"name":"Hasso Plattner Institute University of Potsdam,Potsdam,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojin","family":"Yang","sequence":"additional","affiliation":[{"name":"Hasso Plattner Institute University of Potsdam,Potsdam,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5772\/64211"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17584"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"journal-title":"Neural grafting Repairing the brain and spinal cord","year":"1990","author":"congress","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616244"},{"key":"ref2","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"ref16","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref24","article-title":"Autotiny-bert: Automatic hyper-parameter optimization for efficient pre-trained language models","author":"yin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"journal-title":"You only compress once Towards effective and elastic bert compression via exploitexplore stochastic nature gradient","year":"2021","author":"zhang","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.508"},{"key":"ref28","first-page":"18330","article-title":"Bert loses patience: Fast and robust inference with early exit","volume":"33","author":"zhou","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref8","first-page":"9782","article-title":"Dynabert: Dynamic bert with adaptive width and depth","volume":"33","author":"hou","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"cai","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref4","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"fedus","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref5","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"ar Xiv preprint"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191515.pdf?arnumber=10191515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:33Z","timestamp":1692639753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191515","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}