{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:42Z","timestamp":1740101322783,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020437","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"5632-5638","source":"Crossref","is-referenced-by-count":2,"title":["More is Less \u2013 Byte-quantized models are faster than bit-quantized models on the edge"],"prefix":"10.1109","author":[{"given":"Pengfei","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Shatin,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxia","family":"Han","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shatin,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Lo","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shatin,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scalable methods for 8-bit training of neural networks","author":"Banner","year":"2018","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref3","article-title":"TVM: an automated end-to-end optimizing compiler for deep learning. In Andrea C","volume-title":"OSDI","author":"Chen","year":"2018"},{"key":"ref4","article-title":"MEC: memory-efficient convolution for deep neural network","volume-title":"ICML","author":"Cho","year":"2017"},{"article-title":"Bridging the accuracy gap for 2-bit quantized neural networks (QNN)","year":"2018","author":"Choi","key":"ref5"},{"key":"ref6","article-title":"Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1","author":"Courbariaux","year":"2016","journal-title":"CoRR"},{"key":"ref7","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"Courbariaux","year":"2015","journal-title":"NIPS."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377912"},{"volume-title":"Qnnpack: Open source library for optimized mobile deep learning","year":"2019","author":"Dukhan","key":"ref9"},{"volume-title":"Static quantization with eager mode in pytorch","year":"2020","key":"ref10"},{"key":"ref11","article-title":"Riptide: Fast end-to-end binarized neural networks","author":"Fromm","year":"2020","journal-title":"mlsys"},{"year":"2020","key":"ref12","article-title":"Deploy machine learning models on mobile and iot devices"},{"volume-title":"Post-training quantization","year":"2020","key":"ref13"},{"volume-title":"Ruy","year":"2020","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref19","article-title":"Trained uniform quantization for accurate and efficient neural network inference on fixed-point hardware","author":"Jain","year":"2019","journal-title":"arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/567097.567101"},{"article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","year":"2018","author":"Krishnamoorthi","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","article-title":"Ternary weight networks","author":"Li","year":"2016","journal-title":"arXiv"},{"volume-title":"Acceleration package for neural networks on multi-core cpus","year":"2020","author":"Dukhan","key":"ref24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2389241.2389245"},{"key":"ref29","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/113446.113449"},{"key":"ref32","article-title":"High performance zero-memory overhead direct convolutions","author":"Zhang","year":"2018","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6159"},{"article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","year":"2016","author":"Zhou","key":"ref34"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2022,12,17]]},"location":"Osaka, Japan","end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020437.pdf?arnumber=10020437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T07:41:34Z","timestamp":1707810094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020437\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020437","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}