Accelerating Mobile Edge Generation (MEG) by Constrained Learning

• Published in: IEEE transactions on cognitive communications and networking Vol. 11; no. 3; pp. 1854 - 1869
• Main Authors: Xu, Xiaoxia, Liu, Yuanwei, Mu, Xidong, Xing, Hong, Nallanathan, Arumugam
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Artificial intelligence generated content (AIGC); Computational modeling; Constraints; Diffusion models; Diffusion rate; Edge AI; edge artificial intelligence (AI); Edge computing; Energy consumption; generative AI (GAI); Image coding; Image compression; Image edge detection; Image processing; Image quality; Markov processes; Merging; mobile edge generation (MEG); Mobile handsets; Neurons; Noise reduction; Optimization; reinforcement learning (RL); Videos

A novel mobile edge generation (MEG) framework is proposed for low-latency image generation on mobile devices. Exploiting a latent diffusion model (LDM) distributed across the edge server (ES) and the user equipment (UE), only low-dimension features need to be transmitted for creating artificial int...