{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:45:18Z","timestamp":1730231118686,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447812","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10071-10075","source":"Crossref","is-referenced-by-count":0,"title":["Sensi-Bert: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model"],"prefix":"10.1109","author":[{"given":"Souvik","family":"Kundu","sequence":"first","affiliation":[{"name":"Intel Labs,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharath Nittur","family":"Sridhar","sequence":"additional","affiliation":[{"name":"Intel Labs,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maciej","family":"Szankin","sequence":"additional","affiliation":[{"name":"Intel Labs,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sairam","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"Intel Labs,San Diego,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref1"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref2"},{"article-title":"Albert: A lite bert for self-supervised learning of language representations","year":"2020","author":"Lan","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"article-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","year":"2019","author":"Wang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref7"},{"article-title":"Code llama: Open foundation models for code","year":"2023","author":"Rozi\u00e8re","key":"ref8"},{"article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","year":"2020","author":"Sanh","key":"ref9"},{"article-title":"Tinybert: Distilling bert for natural language understanding","year":"2019","author":"Jiao","key":"ref10"},{"issue":"2","key":"ref11","article-title":"Poor man\u2019s bert: Smaller and faster transformer models","volume":"2","author":"Sajjad","year":"2020"},{"key":"ref12","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume":"33","author":"Sanh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"15834","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":"ref14","first-page":"344","article-title":"Dnr: A tunable robust pruning framework through dynamic network rewiring of dnns","volume-title":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","author":"Kundu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774740"},{"article-title":"Trimbert: Tailoring bert for trade-offs","year":"2022","author":"Sridhar","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"article-title":"Learning to linearize deep neural networks for secure and efficient private inference","volume-title":"International Conference on Learning Representation","author":"Kundu","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"article-title":"Well-read students learn better: On the importance of pre-training compact models","year":"2019","author":"Turc","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"ref25","first-page":"9181","article-title":"Analyzing the confidentiality of undistillable teachers in knowledge distillation","volume":"34","author":"Kundu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304076"},{"article-title":"A broad-coverage challenge corpus for sentence understanding through inference","year":"2017","author":"Williams","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref30","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proceedings of the 2013 conference on empirical methods in natural language processing","author":"Socher"},{"article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Third International Workshop on Paraphrasing (IWP2005)","author":"Dolan","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447812.pdf?arnumber=10447812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:35:17Z","timestamp":1722573317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447812","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}