TY - JOUR
T1 - Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks
T2 - A Survey of AIGC Services
AU - Xu, Minrui
AU - Du, Hongyang
AU - Niyato, Dusit
AU - Kang, Jiawen
AU - Xiong, Zehui
AU - Mao, Shiwen
AU - Han, Zhu
AU - Jamalipour, Abbas
AU - Kim, Dong In
AU - Shen, Xuemin
AU - Leung, Victor C.M.
AU - Poor, H. Vincent
N1 - Publisher Copyright:
© 1998-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Artificial 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.
AB - Artificial 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.
KW - AI training and inference
KW - AIGC
KW - Internet technology
KW - communication and networking
KW - generative AI
KW - mobile edge networks
UR - http://www.scopus.com/inward/record.url?scp=85182935647&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85182935647&partnerID=8YFLogxK
U2 - 10.1109/COMST.2024.3353265
DO - 10.1109/COMST.2024.3353265
M3 - Article
AN - SCOPUS:85182935647
SN - 1553-877X
VL - 26
SP - 1127
EP - 1170
JO - IEEE Communications Surveys and Tutorials
JF - IEEE Communications Surveys and Tutorials
IS - 2
ER -