Parameter Training Efficiency Aware Resource Allocation for AIGC in Space-Air-Ground Integrated Networks

Liangxin Qian, Peiyuan Si, Jun Zhao, Kwok-Yan Lam

Abstract: With the evolution of artificial intelligence-generated content (AIGC) techniques and the development of space-air-ground integrated networks (SAGIN), there will be a growing opportunity to enhance mobile user experiences with customized AIGC applications. This is enabled by combining parameter-efficient fine-tuning (PEFT) with mobile edge computing. In this paper, we formulate the optimization problem of maximizing the parameter training efficiency of the SAGIN system over wireless networks under limited resource constraints. We propose the Parameter training efficiency Aware Resource Allocation (PARA) technique to jointly optimize user association, data offloading, and communication and computational resource allocation. Detailed derivations are presented to solve this difficult sum of ratios problem based on quadratically constrained quadratic programming (QCQP), semidefinite programming (SDP), graph theory, and fractional programming (FP) techniques. Our proposed PARA technique is effective in finding a stationary point of this non-convex problem. The simulation results demonstrate that the proposed PARA method outperforms other baselines.

External IDs:doi:10.1109/tmc.2026.3653031