{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T12:33:40Z","timestamp":1723466020342},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"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":[[2022,5,2]]},"DOI":"10.1109\/infocom48880.2022.9796677","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:18:49Z","timestamp":1655759929000},"source":"Crossref","is-referenced-by-count":8,"title":["Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching"],"prefix":"10.1109","author":[{"given":"Alessandro","family":"Finamore","sequence":"first","affiliation":[{"name":"HUAWEI Technologies,France"}]},{"given":"James","family":"Roberts","sequence":"additional","affiliation":[{"name":"HUAWEI Technologies,France"}]},{"given":"Massimo","family":"Gallo","sequence":"additional","affiliation":[{"name":"HUAWEI Technologies,France"}]},{"given":"Dario","family":"Rossi","sequence":"additional","affiliation":[{"name":"HUAWEI Technologies,France"}]}],"member":"263","reference":[{"key":"ref39","year":"0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.914237"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3122940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3365609.3365864"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-018-0087-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2008.080406"},{"key":"ref37","year":"0"},{"key":"ref36","year":"0"},{"key":"ref35","article-title":"Scikit-learn balltree","year":"0"},{"key":"ref34","article-title":"Model-switching: Dealing with fluctuating workloads in machine-learning-as-a-service systems","author":"zhang","year":"2020","journal-title":"Proc HotCloud"},{"key":"ref28","author":"shakhnarovich","year":"2006","journal-title":"Nearest-Neighbor Methods in Learning and Vision Theory and Practice (Neural Information Processing)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-29151-2"},{"key":"ref29","article-title":"A versatile and accurate approximation for lru cache performance","author":"fricker","year":"2012","journal-title":"Proc ITC"},{"key":"ref2","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3234555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15464-5_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155221"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526769"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6848145"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/TMA.2018.8506558"},{"key":"ref26","author":"samet","year":"2005","journal-title":"Foundations of Multidimensional and Metric Data Structures (The Morgan Kaufmann Series in Computer Graphics and Geometric Modeling)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/502807.502808"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556574"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844983"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186176"},{"key":"ref11","article-title":"Clipper: A low-latency online prediction serving system","author":"crankshaw","year":"2017","journal-title":"Proc NSDI"},{"key":"ref40","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556252"},{"key":"ref13","article-title":"The missing piece in complex analytics: Low latency, scalable model management and serving with velox","author":"crankshaw","year":"2015","journal-title":"Proc CIDR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1117\/12.234785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564763"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1458469.1458473"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1559795.1559815"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.124"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3022227.3022291"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS"},{"key":"ref3","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc NIPS"},{"key":"ref6","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"wang","year":"2019","journal-title":"CoRR"},{"key":"ref5","article-title":"Cloud TPU","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.98"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref9","article-title":"A large scale analysis of hundreds of in-memory cache clusters at twitter","author":"yang","year":"2020","journal-title":"Proc USENIX OSDI"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2011.05.008"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844983"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14778\/2856318.2856324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368303"},{"key":"ref42","article-title":"Lsh was removed from scikit-learn","year":"0"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2615085"},{"key":"ref44","article-title":"Accelerating deep learning inference via freezing","author":"kumar","year":"2019","journal-title":"Proc HotCloud"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"}],"event":{"name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","location":"London, United Kingdom","start":{"date-parts":[[2022,5,2]]},"end":{"date-parts":[[2022,5,5]]}},"container-title":["IEEE INFOCOM 2022 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9796607\/9796652\/09796677.pdf?arnumber=9796677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T20:01:26Z","timestamp":1657569686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9796677\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/infocom48880.2022.9796677","relation":{},"subject":[],"published":{"date-parts":[[2022,5,2]]}}}