<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3966</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>277</issue>
    <volume>2023</volume>
    <articleNumber>110815</articleNumber>
    <type>article</type>
    <publisherName>Elsevier</publisherName>
    <publisherPlace>Amsterdam</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Residual encoding framework to compress DNN parameters for fast transfer</title>
    <parentTitle language="eng">Knowledge-Based Systems</parentTitle>
    <identifier type="issn">1872-7409</identifier>
    <identifier type="issn">0950-7051</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T21:21:35Z","timestamp":1694467295783},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201806270244"]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1016\/j.knosys.2023.110815","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T23:43:49Z","timestamp":1690242229000},"page":"110815","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Residual encoding framework to compress DNN parameters for fast transfer"],"prefix":"10.1016","volume":"277","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-2767-2598","authenticated-orcid":false,"given":"Liguo","family":"Zhou","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7359-1081","authenticated-orcid":false,"given":"Rui","family":"Song","sequence":"additional","affiliation":[]},{"given":"Guang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Festag","sequence":"additional","affiliation":[]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2023.110815_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.106775","article-title":"A survey on federated learning","volume":"216","author":"Zhang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110815_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109929","article-title":"FedStack: Personalized activity monitoring using stacked federated learning","volume":"257","author":"Shaik","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110815_b3","series-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng","year":"2017"},{"issue":"1","key":"10.1016\/j.knosys.2023.110815_b4","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/MSP.2017.2765695","article-title":"Model compression and acceleration for deep neural networks: The principles, progress, and challenges","volume":"35","author":"Cheng","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.knosys.2023.110815_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.108171","article-title":"Deep neural network compression by tucker decomposition with nonlinear response","volume":"241","author":"Liu","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110815_b6","unstructured":"S. Han, H. Mao, W.J. Dally, Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding, in: International Conference on Learning Representations (ICLR), 2016."},{"key":"10.1016\/j.knosys.2023.110815_b7","series-title":"Advances in Neural Information Processing Systems, Vol. 25","article-title":"Large scale distributed deep networks","author":"Dean","year":"2012"},{"key":"10.1016\/j.knosys.2023.110815_b8","article-title":"Communication-efficient algorithms for statistical optimization","volume":"25","author":"Zhang","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2023.110815_b9","article-title":"Trading computation for communication: Distributed stochastic dual coordinate ascent","volume":"26","author":"Yang","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2023.110815_b10","series-title":"International Conference on Machine Learning","first-page":"1973","article-title":"Adding vs. averaging in distributed primal-dual optimization","author":"Ma","year":"2015"},{"key":"10.1016\/j.knosys.2023.110815_b11","series-title":"Large-Scale and Distributed Optimization","first-page":"289","article-title":"Communication-efficient distributed optimization of self-concordant empirical loss","author":"Zhang","year":"2018"},{"key":"10.1016\/j.knosys.2023.110815_b12","unstructured":"B. McMahan, E. Moore, D. Ramage, S. Hampson, B.A.y. Arcas, Communication-Efficient Learning of Deep Networks from Decentralized Data, in: International Conference on Artificial Intelligence and Statistics, Vol. 54, AISTATS, 2017, pp. 1273\u20131282."},{"issue":"4","key":"10.1016\/j.knosys.2023.110815_b13","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"10.1016\/j.knosys.2023.110815_b14","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2023.110815_b15","unstructured":"T. Li, A.K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, V. Smith, Federated optimization in heterogeneous networks, in: Proceedings of Machine Learning and Systems, Vol. 2, 2020, pp. 429\u2013450."},{"key":"10.1016\/j.knosys.2023.110815_b16","series-title":"Federated learning framework coping with hierarchical heterogeneity in cooperative ITS","author":"Song","year":"2022"},{"issue":"7","key":"10.1016\/j.knosys.2023.110815_b17","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s00502-015-0343-0","article-title":"Standards for vehicular communication\u2014from IEEE 802.11 p to 5G","volume":"132","author":"Festag","year":"2015","journal-title":"e &amp; i Elektrotech. Inf.tech."},{"key":"10.1016\/j.knosys.2023.110815_b18","article-title":"Model compression optimized neural network controller for nonlinear systems","author":"Li","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110815_b19","doi-asserted-by":"crossref","unstructured":"Y. He, X. Zhang, J. Sun, Channel pruning for accelerating very deep neural networks, in: Proceedings of the IEEE International Conference on Computer Vision, ICCV, 2017, pp. 1389\u20131397.","DOI":"10.1109\/ICCV.2017.155"},{"key":"10.1016\/j.knosys.2023.110815_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107988","article-title":"DNN compression by ADMM-based joint pruning","volume":"239","author":"Lee","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2023.110815_b21","series-title":"Advances in Neural Information Processing Systems, Vol. 28","article-title":"Structured transforms for small-footprint deep learning","author":"Sindhwani","year":"2015"},{"key":"10.1016\/j.knosys.2023.110815_b22","doi-asserted-by":"crossref","unstructured":"Z. Yang, M. Moczulski, M. Denil, N. de\u00a0Freitas, A. Smola, L. Song, Z. Wang, Deep Fried Convnets, in: Proceedings of the IEEE International Conference on Computer Vision, ICCV, 2015.","DOI":"10.1109\/ICCV.2015.173"},{"issue":"6","key":"10.1016\/j.knosys.2023.110815_b23","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.knosys.2023.110815_b24","article-title":"Learning efficient object detection models with knowledge distillation","volume":"30","author":"Chen","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2023.110815_b25","doi-asserted-by":"crossref","unstructured":"T. Fukuda, M. Suzuki, G. Kurata, S. Thomas, J. Cui, B. Ramabhadran, Efficient Knowledge Distillation from an Ensemble of Teachers, in: Interspeech, 2017, pp. 3697\u20133701.","DOI":"10.21437\/Interspeech.2017-614"},{"key":"10.1016\/j.knosys.2023.110815_b26","series-title":"A study of BFLOAT16 for deep learning training","author":"Kalamkar","year":"2019"},{"issue":"9","key":"10.1016\/j.knosys.2023.110815_b27","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1109\/JPROC.2020.3043399","article-title":"Developments in international video coding standardization after avc, with an overview of versatile video coding (vvc)","volume":"109","author":"Bross","year":"2021","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.knosys.2023.110815_b28","unstructured":"C.-Y. Wu, N. Singhal, P. Krahenbuhl, Video compression through image interpolation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 416\u2013431."},{"key":"10.1016\/j.knosys.2023.110815_b29","series-title":"European Conference on Computer Vision","first-page":"456","article-title":"Content adaptive and error propagation aware deep video compression","author":"Lu","year":"2020"},{"key":"10.1016\/j.knosys.2023.110815_b30","doi-asserted-by":"crossref","unstructured":"A. Djelouah, J. Campos, S. Schaub-Meyer, C. Schroers, Neural inter-frame compression for video coding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, CVPR, 2019, pp. 6421\u20136429.","DOI":"10.1109\/ICCV.2019.00652"},{"key":"10.1016\/j.knosys.2023.110815_b31","doi-asserted-by":"crossref","unstructured":"E. Agustsson, D. Minnen, N. Johnston, J. Balle, S.J. Hwang, G. Toderici, Scale-space flow for end-to-end optimized video compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 8503\u20138512.","DOI":"10.1109\/CVPR42600.2020.00853"},{"issue":"2","key":"10.1016\/j.knosys.2023.110815_b32","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1147\/rd.232.0149","article-title":"Arithmetic coding","volume":"23","author":"Rissanen","year":"1979","journal-title":"IBM J. Res. Dev."},{"key":"10.1016\/j.knosys.2023.110815_b33","article-title":"Deep residual learning","author":"He","year":"2015","journal-title":"Image Recognit."},{"key":"10.1016\/j.knosys.2023.110815_b34","series-title":"ultralytics\/yolov5: v6.1 - TensorRT, TensorFlow edge TPU and OpenVINO export and inference","author":"Jocher","year":"2020"},{"key":"10.1016\/j.knosys.2023.110815_b35","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.knosys.2023.110815_b36","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"issue":"4\u20135","key":"10.1016\/j.knosys.2023.110815_b37","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0925-2312(93)90006-O","article-title":"Backpropagation and stochastic gradient descent method","volume":"5","author":"Amari","year":"1993","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2023.110815_b38","unstructured":"N.-M. Ho, W.-F. Wong, Exploiting half precision arithmetic in Nvidia GPUs, in: 2017 IEEE High Performance Extreme Computing Conference, HPEC, 2017, pp. 1\u20137."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705123005658?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705123005658?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T11:19:25Z","timestamp":1694344765000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705123005658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":38,"alternative-id":["S0950705123005658"],"URL":"http:\/\/dx.doi.org\/10.1016\/j.knosys.2023.110815","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":["Artificial Intelligence","Information Systems and Management","Management Information Systems","Software"],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Residual encoding framework to compress DNN parameters for fast transfer","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2023.110815","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"110815"}}</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="local_crossrefLicence">https://www.elsevier.com/tdm/userlicense/1.0/</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">SubjectUncontrolled_1,SubjectUncontrolled_2,SubjectUncontrolled_3,SubjectUncontrolled_4,PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PublisherName,TitleMain_1,Language,TitleParent_1,ArticleNumber,Volume,CompletedYear,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1016/j.knosys.2023.110815</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_articleversion">published</enrichment>
    <enrichment key="THI_DownloadUrl">https://github.com/zhouliguo/DNN_param_encode</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <author>
      <first_name>Liguo</first_name>
      <last_name>Zhou</last_name>
    </author>
    <author>
      <first_name>Rui</first_name>
      <last_name>Song</last_name>
    </author>
    <author>
      <first_name>Guang</first_name>
      <last_name>Chen</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Festag</last_name>
    </author>
    <author>
      <first_name>Alois</first_name>
      <last_name>Knoll</last_name>
    </author>
    <collection role="institutes" number="19311">Fakultät Elektro- und Informationstechnik</collection>
    <collection role="institutes" number="19319">CARISSMA Institute of Electric, Connected and Secure Mobility (C-ECOS)</collection>
    <collection role="persons" number="25591">Festag, Andreas</collection>
    <collection role="institutes" number="19569">Fraunhofer-Anwendungszentrum "Vernetzte Mobilität und Infrastruktur"</collection>
  </doc>
</export-example>
