{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:18:20Z","timestamp":1759331900116},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Federated learning (FL) is an emerging privacy-preserving technology for machine learning, which enables end devices to cooperatively train a global model without uploading their local sensitive data. Because of limited network bandwidth and considerable communication overhead, communication efficiency has become an essential bottleneck for FL. Existing solutions attempt to improve this situation by reducing communication rounds while usually come with more computation resource consumption or model accuracy deterioration. In this paper, we propose a parameter Prediction-Based DL (PBFL). In which an extended Kalman filter-based prediction algorithm, a practical prediction error threshold setting mechanism and an effective global model updating strategy are included. Instead of collecting all updates from participants, PBFL takes advantage of predicting values to aggregate the model, which substantially reduces required communication rounds while guaranteeing model accuracy. Inspired by the idea of prediction, each participant checks whether its prediction value is out of the tolerance threshold limits and only uploads local updates that have an inaccurate prediction value. In this way, no additional local computational resources are required. Experimental results on both multilayer perceptrons and convolutional neural networks show that PBFL outperforms the state-of-the-art methods and improves the communication efficiency by &amp;gt;66% with 1% higher model accuracy.<\/jats:p>","DOI":"10.1093\/comjnl\/bxab184","type":"journal-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T11:07:45Z","timestamp":1635505665000},"page":"626-642","source":"Crossref","is-referenced-by-count":3,"title":["PBFL: Communication-Efficient Federated Learning via Parameter Predicting"],"prefix":"10.1093","volume":"66","author":[{"given":"Kaiju","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) , Ministry of Education, China, and College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Xiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) , Ministry of Education, China, and College of Computer Science, Chongqing University, Chongqing 400044, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1109\/TSMC.2018.2795609","article-title":"Feature extraction methods for palmprint recognition: A survey and evaluation","volume":"49","author":"Fei","year":"2018","journal-title":"IEEE T. SYST. MAN CY-S."},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","article-title":"Speech recognition using deep neural networks: A systematic review","volume":"7","author":"Nassif","year":"2019","journal-title":"IEEE Access"},{"key":"2023031708554618500_","first-page":"671","article-title":"Deep Learning-Based Hybrid Intelligent Intrusion Detection System","volume":"68","author":"Khan","year":"2021","journal-title":"CMC-COMPUT. MATER. CON."},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"3452","DOI":"10.1109\/JIOT.2017.2762003","article-title":"Crowdtracker: Optimized urban moving object tracking using mobile crowd sensing","volume":"5","author":"Jing","year":"2017","journal-title":"IEEE INTERNET. THINGS."},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"7570","DOI":"10.1109\/JIOT.2019.2901093","article-title":"Crowdtracking: real-time vehicle tracking through mobile crowdsensing","volume":"6","author":"Chen","year":"2019","journal-title":"IEEE INTERNET. THINGS."},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1109\/TMC.2018.2861393","article-title":"Personalized privacy-preserving task allocation for mobile crowdsensing","volume":"18","author":"Wang","year":"2018","journal-title":"IEEE T. MOBILE COMPUT."},{"key":"2023031708554618500_","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Int. Conf. on Artificial Intelligence and Statistics, JMLR: Fort Lauderdale","author":"McMahan","year":"2017"},{"key":"2023031708554618500_","first-page":"1","article-title":"PMF: A privacy-preserving human mobility prediction framework via federated learning","volume-title":"ACM conf. on Interactive, Mobile, Wearable and Ubiquitous Technologies","author":"Feng","year":"2020"},{"key":"2023031708554618500_","first-page":"1","article-title":"Federated learning under channel uncertainty: Joint client scheduling and resource allocation","volume-title":"Int. Conf. on Wireless Communications and Networking Conference","author":"Wadu","year":"2020"},{"key":"2023031708554618500_","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dny","year":"2016"},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1109\/JSAC.2019.2904348","article-title":"Adaptive federated learning in resource constrained edge computing systems","volume":"37","author":"Wang","year":"2019","journal-title":"IEEE J. SEL. AREA. COMM."},{"key":"2023031708554618500_","first-page":"4229","article-title":"Communication-efficient federated deep learning with layerwise asynchronous model update and temporally weighted aggregation","volume":"31","author":"Chen","year":"2019","journal-title":"IEEE T. NEUR. NET. LEAR."},{"key":"2023031708554618500_","first-page":"1310","article-title":"Multi-objective evolutionary federated learning","volume":"31","author":"Zhu","year":"2019","journal-title":"IEEE T. NEUR. NET. LEAR."},{"key":"2023031708554618500_","first-page":"133","article-title":"Training multilayer perceptrons with the extende kalman algorithm","volume-title":"Int. Conf. on Neural Information Processing Systems, ACM","author":"Singhal","year":"1988"},{"key":"2023031708554618500_","first-page":"3461","article-title":"The square-root unscented Kalman filter for state and parameter-estimation","volume-title":"Int. Conf. on Acoustics, Speech, and Signal Processing","author":"Van Der Merwe","year":"2001"},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1109\/COMST.2020.2986024","article-title":"Federated learning in mobile edge networks: A comprehensive survey","volume":"22","author":"Lim","year":"2020","journal-title":"IEEE COMMUN. SURV. TUT."},{"key":"2023031708554618500_","article-title":"Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977","author":"Kairouz","year":"2019"},{"key":"2023031708554618500_","first-page":"1","article-title":"Two-stream federated learning: Reduce the communication costs","volume-title":"Int. Conf. on Visual Communications and Image Processing","author":"Yao","year":"2018"},{"key":"2023031708554618500_","first-page":"2200","article-title":"Transfer feature learning with joint distribution adaptation","volume-title":"Int. Conf. on Computer Vision","author":"Long","year":"2013"},{"key":"2023031708554618500_","first-page":"175","article-title":"Towards faster and better federated learning: A feature fusion approach","volume-title":"Int. Conf. on Image Processing","author":"Yao","year":"2019"},{"key":"2023031708554618500_","first-page":"1488","article-title":"Scalable distributed DNN training using commodity GPU cloud computing","volume-title":"Int. Conf. on Speech Communication Association","author":"Strom","year":"2015"},{"key":"2023031708554618500_","first-page":"1","volume-title":"esgd: Communication efficient distributed deep learning on the edge. USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)","author":"Tao","year":"2018"},{"key":"2023031708554618500_","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Int. Conf. on Networked Systems Design and Implementation","author":"Hsieh","year":"2018"},{"key":"2023031708554618500_","first-page":"954","article-title":"CMFL: Mitigating communication overhead for federated learning","volume-title":"Int. Conf. on Distributed Computing Systems","author":"Luping","year":"2019"},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE T. NEUR. NET. LEAR."},{"key":"2023031708554618500_","first-page":"1","article-title":"Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization","volume":"99","author":"Cui","year":"2014","journal-title":"IEEE T. FUZZY. SYST."},{"key":"2023031708554618500_","first-page":"436","volume":"521","author":"Lecun","year":"2015","journal-title":"Deep learning. NATURE"},{"key":"2023031708554618500_","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1109\/78.774779","article-title":"The extended Kalman filter as an exponential observer for nonlinear systems","volume":"47","author":"Reif","year":"1999","journal-title":"IEEE T. SIGNAL. PROCES."},{"key":"2023031708554618500_","first-page":"3","article-title":"Neural Networks In Engineering","volume":"6","author":"Pham","year":"1970","journal-title":"WIT Transactions on Information and Communication Technologies"},{"key":"2023031708554618500_","first-page":"1","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"The handbook of brain theory & neural networks"},{"key":"2023031708554618500_","first-page":"2278","article-title":"Gradient-based learning applied to document recognition","author":"Lecun","year":"1998"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/3\/626\/49531034\/bxab184.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/3\/626\/49531034\/bxab184.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T22:59:53Z","timestamp":1699743593000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/66\/3\/626\/6438106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,11,24]]},"published-print":{"date-parts":[[2023,3,15]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxab184","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,3]]},"published":{"date-parts":[[2021,11,24]]}}}