File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services

TitleUnleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services
Authors
KeywordsAI training and inference
AIGC
communication and networking
generative AI
Internet technology
mobile edge networks
Issue Date2024
Citation
IEEE Communications Surveys and Tutorials, 2024, v. 26, n. 2, p. 1127-1170 How to Cite?
AbstractArtificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. This survey paper focuses on the deployment of AIGC applications, e.g., ChatGPT and Dall-E, at mobile edge networks, namely mobile AIGC networks, that provide personalized and customized AIGC services in real time while maintaining user privacy. We begin by introducing the background and fundamentals of generative models and the lifecycle of AIGC services at mobile AIGC networks, which includes data collection, training, fine-tuning, inference, and product management. We then discuss the collaborative cloud-edge-mobile infrastructure and technologies required to support AIGC services and enable users to access AIGC at mobile edge networks. Furthermore, we explore AIGC-driven creative applications and use cases for mobile AIGC networks. Additionally, we discuss the implementation, security, and privacy challenges of deploying mobile AIGC networks. Finally, we highlight some future research directions and open issues for the full realization of mobile AIGC networks.
Persistent Identifierhttp://hdl.handle.net/10722/353137
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXu, Minrui-
dc.contributor.authorDu, Hongyang-
dc.contributor.authorNiyato, Dusit-
dc.contributor.authorKang, Jiawen-
dc.contributor.authorXiong, Zehui-
dc.contributor.authorMao, Shiwen-
dc.contributor.authorHan, Zhu-
dc.contributor.authorJamalipour, Abbas-
dc.contributor.authorKim, Dong In-
dc.contributor.authorShen, Xuemin-
dc.contributor.authorLeung, Victor C.M.-
dc.contributor.authorPoor, H. Vincent-
dc.date.accessioned2025-01-13T03:02:16Z-
dc.date.available2025-01-13T03:02:16Z-
dc.date.issued2024-
dc.identifier.citationIEEE Communications Surveys and Tutorials, 2024, v. 26, n. 2, p. 1127-1170-
dc.identifier.urihttp://hdl.handle.net/10722/353137-
dc.description.abstractArtificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. This survey paper focuses on the deployment of AIGC applications, e.g., ChatGPT and Dall-E, at mobile edge networks, namely mobile AIGC networks, that provide personalized and customized AIGC services in real time while maintaining user privacy. We begin by introducing the background and fundamentals of generative models and the lifecycle of AIGC services at mobile AIGC networks, which includes data collection, training, fine-tuning, inference, and product management. We then discuss the collaborative cloud-edge-mobile infrastructure and technologies required to support AIGC services and enable users to access AIGC at mobile edge networks. Furthermore, we explore AIGC-driven creative applications and use cases for mobile AIGC networks. Additionally, we discuss the implementation, security, and privacy challenges of deploying mobile AIGC networks. Finally, we highlight some future research directions and open issues for the full realization of mobile AIGC networks.-
dc.languageeng-
dc.relation.ispartofIEEE Communications Surveys and Tutorials-
dc.subjectAI training and inference-
dc.subjectAIGC-
dc.subjectcommunication and networking-
dc.subjectgenerative AI-
dc.subjectInternet technology-
dc.subjectmobile edge networks-
dc.titleUnleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/COMST.2024.3353265-
dc.identifier.scopuseid_2-s2.0-85182935647-
dc.identifier.volume26-
dc.identifier.issue2-
dc.identifier.spage1127-
dc.identifier.epage1170-
dc.identifier.eissn1553-877X-
dc.identifier.isiWOS:001230185600001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats