{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:04Z","timestamp":1730230684157,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096107","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["A Probabilistic Framework for Pruning Transformers Via a Finite Admixture of Keys"],"prefix":"10.1109","author":[{"given":"Tan M.","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of California,Department of Mathematics,Los Angeles,USA"}]},{"given":"Tam","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Rice University,Department of Electrical and Computer Engineering,Houston,USA"}]},{"given":"Long","family":"Bui","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Ha Noi,Vietnam"}]},{"given":"Hai","family":"Do","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Ha Noi,Vietnam"}]},{"given":"Duy Khuong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Ha Noi,Vietnam"}]},{"given":"Dung D.","family":"Le","sequence":"additional","affiliation":[{"name":"Vin University,College of Engineering and Computer Science,Vietnam"}]},{"given":"Hung","family":"Tran-The","sequence":"additional","affiliation":[{"name":"Deakin University,Applied Artificial Intelligence Institute,Geelong,Australia"}]},{"given":"Nhat","family":"Ho","sequence":"additional","affiliation":[{"name":"The University of Texas,Department of Statistics and Data Sciences,Austin,USA"}]},{"given":"Stan J.","family":"Osher","sequence":"additional","affiliation":[{"name":"University of California,Department of Mathematics,Los Angeles,USA"}]},{"given":"Richard G.","family":"Baraniuk","sequence":"additional","affiliation":[{"name":"Rice University,Department of Electrical and Computer Engineering,Houston,USA"}]}],"member":"263","reference":[{"journal-title":"Analyzing multi-head self-attention Specialized heads do the heavy lifting the rest can be pruned","year":"2019","author":"voita","key":"ref13"},{"key":"ref12","article-title":"Are sixteen heads really better than one?","author":"michel","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Learned token pruning for transformers","year":"2021","author":"kim","key":"ref23"},{"key":"ref15","article-title":"Improving transformer with an admixture of attention heads","author":"nguyen","year":"2022","journal-title":"Advances in neural information processing systems"},{"journal-title":"Eigen analysis of self-attention and its reconstruction from partial computation","year":"2021","author":"bhojanapalli","key":"ref14"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00436"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.508"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref21","article-title":"Power-bert: Accelerating bert inference via progressive word-vector elimination","author":"goyal","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"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","first-page":"19974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume":"34","author":"chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Improving transformers with probabilistic attention keys","author":"nguyen","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref18","article-title":"Pointer sentinel mixture models","author":"merity","year":"2017","journal-title":"International Conference on Learning Representations"},{"journal-title":"RoBERTa A Robustly optimized BERT Pretraining Approach","year":"2019","author":"liu","key":"ref8"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"journal-title":"An image is worth 16x16 words Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref6","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018","journal-title":"OpenAI report"},{"key":"ref5","article-title":"Training data-efficient image transformers amp; distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096107.pdf?arnumber=10096107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:47Z","timestamp":1700507207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096107","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}