{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:09:04Z","timestamp":1730221744323,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T00:00:00Z","timestamp":1694995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T00:00:00Z","timestamp":1694995200000},"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":[[2023,9,18]]},"DOI":"10.1109\/fmec59375.2023.10306211","type":"proceedings-article","created":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T13:51:37Z","timestamp":1699451497000},"page":"247-253","source":"Crossref","is-referenced-by-count":0,"title":["Federated Boolean Neural Networks Learning"],"prefix":"10.1109","author":[{"given":"Louis","family":"Leconte","sequence":"first","affiliation":[{"name":"LISITE, Sorbonne University,Paris,France"}]},{"given":"Van Minh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Mathematical and Algorithmic Sciences Lab,Paris,France"}]},{"given":"Eric","family":"Moulines","sequence":"additional","affiliation":[{"name":"CMAP, Ecole Polytechnique,Paris,France"}]}],"member":"263","reference":[{"year":"2021","author":"leconte","journal-title":"Dostovoq Doubly stochastic voronoi vector quantization sgd for federated learning","key":"ref13"},{"year":"2022","author":"nguyen","journal-title":"Device and method for a boolean neural network","key":"ref12"},{"key":"ref15","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"ArXiv"},{"year":"2022","author":"nguyen","journal-title":"A device and method for processing a convolutional neural network with binary weights","key":"ref14"},{"key":"ref11","article-title":"Fedqnn: a computation-communication efficient federated learning framework for iot with low-bitwidth neural network quantization","author":"ji","year":"2022","journal-title":"IEEE Internet of Things Journal"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-3-031-20083-0_23"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR42600.2020.00154"},{"key":"ref16","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR46437.2021.00499"},{"key":"ref18","article-title":"F8Net: Fixed-point 8-bit only multiplication for network quantization","author":"jin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref50","article-title":"Asynchronous sgd beats minibatch sgd under arbitrary delays","author":"mishchenko","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref46","first-page":"143","article-title":"React-net: Towards precise binary neural network with gener-alized activation functions","author":"liu","year":"0","journal-title":"European Conference on Computer Vision"},{"year":"2009","author":"krizhevsky","journal-title":"Learning multiple layers of features from tiny images","key":"ref45"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref47","article-title":"Quafl: Federated averaging can be both asynchronous and communication-efficient","author":"zakerinia","year":"2022","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/ICASSP39728.2021.9413697"},{"key":"ref41","article-title":"Adaptive compression for communication-efficient distributed training","author":"makarenko","year":"2022","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref43","article-title":"Feddq: Communication-efficient federated learning with descending quantization","author":"qu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref49","article-title":"Favas: Federated averaging with asynchronous clients","author":"leconte","year":"2023","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Askewsgd: An annealed interval-constrained optimisation method to train quantized neural networks","author":"leconte","year":"2022","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref9","article-title":"Logarithmic unbiased quantization: Sim-ple 4-bit training in deep learning","author":"chmiel","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"A field guide to federated optimization","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1561\/9781680837896"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref5","first-page":"3123","article-title":"Binarycon-nect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1145\/3510587"},{"key":"ref35","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"0","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref34","article-title":"Performance optimization for variable bitwidth federated learning in wireless networks","author":"wang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref37","first-page":"560","article-title":"signsgd: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref36","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","volume":"30","author":"alistarh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Bridging the accuracy gap for 2-bit quantized neural networks (qnn)","author":"choi","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref30","first-page":"1796","article-title":"Ultra-low precision 4-bit training of deep neural networks","volume":"33","author":"sun","year":"2020","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/JSAC.2021.3118415"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/CVPR.2019.00066"},{"key":"ref2","article-title":"Fedshuffle: Recipes for better use of local work in federated learning","author":"horv\u00e1th","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Federated learning with non-iid data","author":"zhao","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref39","article-title":"Dasha: Distributed noncon-vex optimization with communication compression, op-timal oracle complexity, and no client synchronization","author":"tyurin","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref38","first-page":"3788","article-title":"Marina: Faster non-convex distributed learning with compression","author":"gorbunov","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref24","article-title":"A white paper on neural network quantization","author":"nagel","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"A survey on methods and theories of quan-tized neural networks","author":"guo","year":"2018","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1609\/aaai.v32i1.11660"},{"key":"ref25","article-title":"Binarized neural networks","volume":"29","author":"hubara","year":"2016","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TNNLS.2021.3069886"},{"key":"ref22","article-title":"A review of recent advances of binary neural networks for edge computing","author":"zhao","year":"2020","journal-title":"IEEE Journal on Miniaturization for Air and Space Systems"},{"key":"ref21","first-page":"291","author":"gholami","year":"0","journal-title":"Low-Power Computer Vision"},{"key":"ref28","article-title":"Adaste: An adaptive straight-through estimator to train binary neural networks","author":"le","year":"2021","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref29","article-title":"The high-dimensional geometry of binary neural networks","author":"anderson","year":"2018","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC)","start":{"date-parts":[[2023,9,18]]},"location":"Tartu, Estonia","end":{"date-parts":[[2023,9,20]]}},"container-title":["2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10305711\/10305726\/10306211.pdf?arnumber=10306211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T14:22:48Z","timestamp":1702304568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10306211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,18]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/fmec59375.2023.10306211","relation":{},"subject":[],"published":{"date-parts":[[2023,9,18]]}}}