面向空间-空-地一体化网络的参数训练效率感知资源分配
Parameter Training Efficiency Aware Resource Allocation for AIGC in Space-Air-Ground Integrated Networks
AI总结:
本文提出PARA技术,通过联合优化用户关联、数据卸载和资源分配,提升空间-空-地一体化网络中参数训练效率,从而提高AIGC应用的移动体验。
摘要:
随着人工智能生成内容(AIGC)技术的发展和空间-空-地一体化网络(SAGIN)的发展,通过参数高效微调(PEFT)训练与移动边缘计算相结合,将为更多用户提供定制化的AIGC应用,从而提升移动体验。本文提出了在无线网络受限资源条件下,最大化SAGIN系统参数训练效率的优化问题。我们提出参数训练效率感知资源分配(PARA)技术,用于联合优化用户关联、数据卸载和通信与计算资源分配。通过二次约束二次规划(QCQP)、半正定规划(SDP)、图论和分数规划(FP)技术,给出了解决该复杂比率和问题的严谨证明。所提出的PARA技术能够有效找到该非凸问题的 stationary 点。仿真结果表明,所提出的PARA方法在性能上优于其他基线方法。
英文摘要:
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 more users' mobile experience with customized AIGC applications. This is made possible through the use of parameter-efficient fine-tuning (PEFT) training alongside 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. Solid proofs 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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。