Accelerating Mobile Edge Generation (MEG) by Constrained Learning

TL;DR

This paper introduces a novel framework for high-resolution image generation on mobile devices using distributed large-scale latent diffusion models, optimizing quality, latency, and energy consumption through constrained learning.

Contribution

It proposes a low-complexity accelerated mobile edge generation protocol with a constrained variational policy optimization algorithm for efficient, high-quality image synthesis under resource constraints.

Findings

Achieves 1024x1024 high-quality images over noisy channels.

Reduces latency by over 40% compared to traditional methods.

Effectively balances image quality and generation costs using MEG-CVPO.

Abstract

A novel accelerated mobile edge generation (MEG) framework is proposed for generating high-resolution images on mobile devices. Exploiting a large-scale latent diffusion model (LDM) distributed across edge server (ES) and user equipment (UE), cost-efficient artificial intelligence generated content (AIGC) is achieved by transmitting low-dimensional features between ES and UE. To reduce overheads of both distributed computations and transmissions, a dynamic diffusion and feature merging scheme is conceived. By jointly optimizing the denoising steps and feature merging ratio, the image generation quality is maximized subject to latency and energy consumption constraints. To address this problem and tailor LDM sub-models, a low-complexity MEG acceleration protocol is developed. Particularly, a backbone meta-architecture is trained via offline distillation. Then, dynamic diffusion and feature merging are determined in online channel environment, which can be viewed as a constrained Markov Decision Process (MDP). A constrained variational policy optimization (CVPO) based MEG algorithm is further proposed for constraint-guaranteed learning, namely MEG-CVPO. Numerical results verify that: 1) The proposed framework can generate 1024$\times$1024 high-quality images over noisy channels while reducing over $40\%$ latency compared to conventional generation schemes. 2) The developed MEG-CVPO effectively mitigates constraint violations, thus flexibly controlling the trade-off between image distortion and generation costs.