{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:24:16Z","timestamp":1730269456320,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"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":[[2023,11,17]]},"DOI":"10.1109\/ipccc59175.2023.10253832","type":"proceedings-article","created":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T17:44:32Z","timestamp":1697651072000},"page":"481-487","source":"Crossref","is-referenced-by-count":0,"title":["A Model Compression Method Using Significant Data and Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Fan","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,ZhouShan,China"}]},{"given":"Beibei","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanjing Tech University,NanJing,China"}]},{"given":"Kai","family":"Cui","sequence":"additional","affiliation":[{"name":"Nanjing Tech University,NanJing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01294"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-5225-2255-3.ch011"},{"issue":"5","key":"ref3","first-page":"14","volume-title":"Lenet-5, convolutional neural networks","volume":"20","author":"LeCun","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"volume-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC.2016.7867471"},{"issue":"7","key":"ref10","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"Hinton","year":"2015","journal-title":"arXiv preprint arXiv:1503.02531"},{"key":"ref11","first-page":"5186","article-title":"Dataset distillation with infinitely wide convolutional networks","volume":"34","author":"Nguyen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Beyond neural scaling laws: beating power law scaling via data pruning","author":"Sorscher","year":"2022","journal-title":"arXiv preprint arXiv:2206.14486"},{"key":"ref13","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv preprint arXiv:1412.6550"},{"key":"ref14","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"Mishra","year":"2017","journal-title":"arXiv preprint arXiv:1711.05852"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref15"},{"key":"ref16","first-page":"19 920","article-title":"Estimating training data influence by tracing gradient descent","volume":"33","author":"Pruthi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.419"},{"key":"ref18","article-title":"Representer point selection for explaining deep neural networks","volume":"31","author":"Yeh","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"International conference on machine learning","author":"Koh"},{"issue":"1","key":"ref20","first-page":"226","article-title":"Knowledge matters: Importance of prior information for optimization","volume":"17","author":"G\u00fcl\u00e7ehre","year":"2016","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"2023 IEEE International Performance, Computing, and Communications Conference (IPCCC)","start":{"date-parts":[[2023,11,17]]},"location":"Anaheim, CA, USA","end":{"date-parts":[[2023,11,19]]}},"container-title":["2023 IEEE International Performance, Computing, and Communications Conference (IPCCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10253817\/10253818\/10253832.pdf?arnumber=10253832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T02:33:32Z","timestamp":1709346812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10253832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,17]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ipccc59175.2023.10253832","relation":{},"subject":[],"published":{"date-parts":[[2023,11,17]]}}}