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
• ISSN: 2332-7731; 2332-7731
• DOI: 10.1109/TCCN.2025.3558975

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 intelligence generative content (AIGC). Two novel modules, namely dynamic diffusion and feature merging, are conceived to compress the diffusion model and transmitted features, respectively. By jointly optimizing compression rates of denoising steps and feature merging, the image quality maximization problem is formulated subject to latency and energy consumption constraints. To address this problem in dynamic channel conditions, a low-complexity compression protocol is developed. First, a backbone LDM architecture is learned by offline distillation to support various compression options. Then, compression rates are predicted in online environment specific to channel and task features. To solve the resultant constrained Markov Decision Process (MDP), a constrained variational policy optimization (CVPO) based MEG algorithm, MEG-CVPO , is further developed to learn constraint-guaranteed optimization. Numerical results demonstrate that: 1) The proposed framework improves image distortions while reducing over 40% latency compared to conventional generation schemes. 2) MEG-CVPO stringently guarantee constraints and realizes a flexible trade-off between generation qualities and overheads. Code is available at https://github.com/xiaoxiaxusummer/LowLatencyMEG .