Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on knowledge and data engineering 2023-07, Vol.35 (7), p.6866-6886 |
---|---|
Hauptverfasser: | , , , , , , , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 6886 |
---|---|
container_issue | 7 |
container_start_page | 6866 |
container_title | IEEE transactions on knowledge and data engineering |
container_volume | 35 |
creator | Yao, Jiangchao Zhang, Shengyu Yao, Yang Wang, Feng Ma, Jianxin Zhang, Jianwei Chu, Yunfei Ji, Luo Jia, Kunyang Shen, Tao Wu, Anpeng Zhang, Fengda Tan, Ziqi Kuang, Kun Wu, Chao Wu, Fei Zhou, Jingren Yang, Hongxia |
description | Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field. |
doi_str_mv | 10.1109/TKDE.2022.3178211 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TKDE_2022_3178211</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9783185</ieee_id><sourcerecordid>2823193636</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-37ce2833ba4cc548ec5323dca30e0f3de3296857c65549553500a660f4e12e213</originalsourceid><addsrcrecordid>eNo9kEFLw0AQhRdRsFZ_gHgJeE7d2ckmG28lVlssKFjPy3Yz0ZQ0W3ebQv31plZkDjM83psHH2PXwEcAPL9bPD9MRoILMULIlAA4YQOQUsUCcjjtb55AnGCSnbOLEFacc5UpGLDppPyguGhcV0avrjG-_jbb2rWRacuocE1jls7_KvfRuBfWG0-f1IZ6R9Fb53e0jyrno_Hskp1Vpgl09beH7P1xsiim8fzlaVaM57EVOW5jzCwJhbg0ibUyUWQlCiytQU68wpJQ5KmSmU2lTHIpUXJu0pRXCYEgAThkt8e_G---OgpbvXKdb_tKLZRAyDHtZ8jg6LLeheCp0htfr43fa-D6AEwfgOkDMP0HrM_cHDM1Ef3780whKIk_FvZk4g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2823193636</pqid></control><display><type>article</type><title>Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI</title><source>IEEE Electronic Library (IEL)</source><creator>Yao, Jiangchao ; Zhang, Shengyu ; Yao, Yang ; Wang, Feng ; Ma, Jianxin ; Zhang, Jianwei ; Chu, Yunfei ; Ji, Luo ; Jia, Kunyang ; Shen, Tao ; Wu, Anpeng ; Zhang, Fengda ; Tan, Ziqi ; Kuang, Kun ; Wu, Chao ; Wu, Fei ; Zhou, Jingren ; Yang, Hongxia</creator><creatorcontrib>Yao, Jiangchao ; Zhang, Shengyu ; Yao, Yang ; Wang, Feng ; Ma, Jianxin ; Zhang, Jianwei ; Chu, Yunfei ; Ji, Luo ; Jia, Kunyang ; Shen, Tao ; Wu, Anpeng ; Zhang, Fengda ; Tan, Ziqi ; Kuang, Kun ; Wu, Chao ; Wu, Fei ; Zhou, Jingren ; Yang, Hongxia</creatorcontrib><description>Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.</description><identifier>ISSN: 1041-4347</identifier><identifier>EISSN: 1558-2191</identifier><identifier>DOI: 10.1109/TKDE.2022.3178211</identifier><identifier>CODEN: ITKEEH</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Artificial intelligence ; Cloud AI ; Cloud computing ; Collaboration ; Computational modeling ; Deep learning ; edge AI ; Edge computing ; edge-cloud collaboration ; Graph neural networks ; Hardware ; Internet of Things ; Machine learning ; R&D ; Research & development</subject><ispartof>IEEE transactions on knowledge and data engineering, 2023-07, Vol.35 (7), p.6866-6886</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-37ce2833ba4cc548ec5323dca30e0f3de3296857c65549553500a660f4e12e213</citedby><cites>FETCH-LOGICAL-c293t-37ce2833ba4cc548ec5323dca30e0f3de3296857c65549553500a660f4e12e213</cites><orcidid>0000-0003-3898-7122 ; 0000-0003-0885-6869 ; 0000-0002-0030-8289 ; 0000-0002-0580-9728 ; 0000-0001-7024-9790 ; 0000-0002-2484-5345 ; 0000-0001-6115-5194 ; 0000-0003-2139-8807</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9783185$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9783185$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yao, Jiangchao</creatorcontrib><creatorcontrib>Zhang, Shengyu</creatorcontrib><creatorcontrib>Yao, Yang</creatorcontrib><creatorcontrib>Wang, Feng</creatorcontrib><creatorcontrib>Ma, Jianxin</creatorcontrib><creatorcontrib>Zhang, Jianwei</creatorcontrib><creatorcontrib>Chu, Yunfei</creatorcontrib><creatorcontrib>Ji, Luo</creatorcontrib><creatorcontrib>Jia, Kunyang</creatorcontrib><creatorcontrib>Shen, Tao</creatorcontrib><creatorcontrib>Wu, Anpeng</creatorcontrib><creatorcontrib>Zhang, Fengda</creatorcontrib><creatorcontrib>Tan, Ziqi</creatorcontrib><creatorcontrib>Kuang, Kun</creatorcontrib><creatorcontrib>Wu, Chao</creatorcontrib><creatorcontrib>Wu, Fei</creatorcontrib><creatorcontrib>Zhou, Jingren</creatorcontrib><creatorcontrib>Yang, Hongxia</creatorcontrib><title>Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI</title><title>IEEE transactions on knowledge and data engineering</title><addtitle>TKDE</addtitle><description>Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Cloud AI</subject><subject>Cloud computing</subject><subject>Collaboration</subject><subject>Computational modeling</subject><subject>Deep learning</subject><subject>edge AI</subject><subject>Edge computing</subject><subject>edge-cloud collaboration</subject><subject>Graph neural networks</subject><subject>Hardware</subject><subject>Internet of Things</subject><subject>Machine learning</subject><subject>R&D</subject><subject>Research & development</subject><issn>1041-4347</issn><issn>1558-2191</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kEFLw0AQhRdRsFZ_gHgJeE7d2ckmG28lVlssKFjPy3Yz0ZQ0W3ebQv31plZkDjM83psHH2PXwEcAPL9bPD9MRoILMULIlAA4YQOQUsUCcjjtb55AnGCSnbOLEFacc5UpGLDppPyguGhcV0avrjG-_jbb2rWRacuocE1jls7_KvfRuBfWG0-f1IZ6R9Fb53e0jyrno_Hskp1Vpgl09beH7P1xsiim8fzlaVaM57EVOW5jzCwJhbg0ibUyUWQlCiytQU68wpJQ5KmSmU2lTHIpUXJu0pRXCYEgAThkt8e_G---OgpbvXKdb_tKLZRAyDHtZ8jg6LLeheCp0htfr43fa-D6AEwfgOkDMP0HrM_cHDM1Ef3780whKIk_FvZk4g</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Yao, Jiangchao</creator><creator>Zhang, Shengyu</creator><creator>Yao, Yang</creator><creator>Wang, Feng</creator><creator>Ma, Jianxin</creator><creator>Zhang, Jianwei</creator><creator>Chu, Yunfei</creator><creator>Ji, Luo</creator><creator>Jia, Kunyang</creator><creator>Shen, Tao</creator><creator>Wu, Anpeng</creator><creator>Zhang, Fengda</creator><creator>Tan, Ziqi</creator><creator>Kuang, Kun</creator><creator>Wu, Chao</creator><creator>Wu, Fei</creator><creator>Zhou, Jingren</creator><creator>Yang, Hongxia</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-3898-7122</orcidid><orcidid>https://orcid.org/0000-0003-0885-6869</orcidid><orcidid>https://orcid.org/0000-0002-0030-8289</orcidid><orcidid>https://orcid.org/0000-0002-0580-9728</orcidid><orcidid>https://orcid.org/0000-0001-7024-9790</orcidid><orcidid>https://orcid.org/0000-0002-2484-5345</orcidid><orcidid>https://orcid.org/0000-0001-6115-5194</orcidid><orcidid>https://orcid.org/0000-0003-2139-8807</orcidid></search><sort><creationdate>20230701</creationdate><title>Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI</title><author>Yao, Jiangchao ; Zhang, Shengyu ; Yao, Yang ; Wang, Feng ; Ma, Jianxin ; Zhang, Jianwei ; Chu, Yunfei ; Ji, Luo ; Jia, Kunyang ; Shen, Tao ; Wu, Anpeng ; Zhang, Fengda ; Tan, Ziqi ; Kuang, Kun ; Wu, Chao ; Wu, Fei ; Zhou, Jingren ; Yang, Hongxia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-37ce2833ba4cc548ec5323dca30e0f3de3296857c65549553500a660f4e12e213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Cloud AI</topic><topic>Cloud computing</topic><topic>Collaboration</topic><topic>Computational modeling</topic><topic>Deep learning</topic><topic>edge AI</topic><topic>Edge computing</topic><topic>edge-cloud collaboration</topic><topic>Graph neural networks</topic><topic>Hardware</topic><topic>Internet of Things</topic><topic>Machine learning</topic><topic>R&D</topic><topic>Research & development</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yao, Jiangchao</creatorcontrib><creatorcontrib>Zhang, Shengyu</creatorcontrib><creatorcontrib>Yao, Yang</creatorcontrib><creatorcontrib>Wang, Feng</creatorcontrib><creatorcontrib>Ma, Jianxin</creatorcontrib><creatorcontrib>Zhang, Jianwei</creatorcontrib><creatorcontrib>Chu, Yunfei</creatorcontrib><creatorcontrib>Ji, Luo</creatorcontrib><creatorcontrib>Jia, Kunyang</creatorcontrib><creatorcontrib>Shen, Tao</creatorcontrib><creatorcontrib>Wu, Anpeng</creatorcontrib><creatorcontrib>Zhang, Fengda</creatorcontrib><creatorcontrib>Tan, Ziqi</creatorcontrib><creatorcontrib>Kuang, Kun</creatorcontrib><creatorcontrib>Wu, Chao</creatorcontrib><creatorcontrib>Wu, Fei</creatorcontrib><creatorcontrib>Zhou, Jingren</creatorcontrib><creatorcontrib>Yang, Hongxia</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on knowledge and data engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yao, Jiangchao</au><au>Zhang, Shengyu</au><au>Yao, Yang</au><au>Wang, Feng</au><au>Ma, Jianxin</au><au>Zhang, Jianwei</au><au>Chu, Yunfei</au><au>Ji, Luo</au><au>Jia, Kunyang</au><au>Shen, Tao</au><au>Wu, Anpeng</au><au>Zhang, Fengda</au><au>Tan, Ziqi</au><au>Kuang, Kun</au><au>Wu, Chao</au><au>Wu, Fei</au><au>Zhou, Jingren</au><au>Yang, Hongxia</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI</atitle><jtitle>IEEE transactions on knowledge and data engineering</jtitle><stitle>TKDE</stitle><date>2023-07-01</date><risdate>2023</risdate><volume>35</volume><issue>7</issue><spage>6866</spage><epage>6886</epage><pages>6866-6886</pages><issn>1041-4347</issn><eissn>1558-2191</eissn><coden>ITKEEH</coden><abstract>Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TKDE.2022.3178211</doi><tpages>21</tpages><orcidid>https://orcid.org/0000-0003-3898-7122</orcidid><orcidid>https://orcid.org/0000-0003-0885-6869</orcidid><orcidid>https://orcid.org/0000-0002-0030-8289</orcidid><orcidid>https://orcid.org/0000-0002-0580-9728</orcidid><orcidid>https://orcid.org/0000-0001-7024-9790</orcidid><orcidid>https://orcid.org/0000-0002-2484-5345</orcidid><orcidid>https://orcid.org/0000-0001-6115-5194</orcidid><orcidid>https://orcid.org/0000-0003-2139-8807</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1041-4347 |
ispartof | IEEE transactions on knowledge and data engineering, 2023-07, Vol.35 (7), p.6866-6886 |
issn | 1041-4347 1558-2191 |
language | eng |
recordid | cdi_crossref_primary_10_1109_TKDE_2022_3178211 |
source | IEEE Electronic Library (IEL) |
subjects | Algorithms Artificial intelligence Cloud AI Cloud computing Collaboration Computational modeling Deep learning edge AI Edge computing edge-cloud collaboration Graph neural networks Hardware Internet of Things Machine learning R&D Research & development |
title | Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T03%3A43%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Edge-Cloud%20Polarization%20and%20Collaboration:%20A%20Comprehensive%20Survey%20for%20AI&rft.jtitle=IEEE%20transactions%20on%20knowledge%20and%20data%20engineering&rft.au=Yao,%20Jiangchao&rft.date=2023-07-01&rft.volume=35&rft.issue=7&rft.spage=6866&rft.epage=6886&rft.pages=6866-6886&rft.issn=1041-4347&rft.eissn=1558-2191&rft.coden=ITKEEH&rft_id=info:doi/10.1109/TKDE.2022.3178211&rft_dat=%3Cproquest_RIE%3E2823193636%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2823193636&rft_id=info:pmid/&rft_ieee_id=9783185&rfr_iscdi=true |