arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04430cs.LGcs.DCcs.NI
收藏

面向移动边缘网络中绿色联邦生成扩散的按需量化

On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks

School of Automation, Guangdong University of Technology(广东工业大学自动化学院);School of Electronics Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院);School of Software Engineering, Beijing Jiaotong University(北京交通大学软件学院)

Bingkun Lai, Jiayi He, Jiawen Kang, Gaolei Li, Minrui Xu, Tao zhang, Shengli Xie

AI总结:

针对移动边缘网络中联邦训练生成扩散模型的高通信与能耗问题,提出按需量化节能联邦扩散方法,可适配边缘设备需求,在保障生成数据质量与多样性的同时显著降低能耗与传输量。

摘要:

生成式人工智能(GAI)在元宇宙、工业物联网等移动边缘网络场景中展现出卓越的生产力与创造力。受数据分布特性影响,联邦学习是在移动边缘网络中高效训练GAI模型的可行技术。然而,在移动边缘网络中训练生成扩散模型这类大型GAI模型时,通信开销问题十分突出。此外,扩散类模型训练的高能耗、边缘设备资源有限以及网络环境复杂,都为提升GAI模型训练效率带来了挑战。为应对这一难题,本文提出一种适用于移动边缘网络的按需量化节能联邦扩散方法。具体而言,我们首先设计了一种动态量化联邦扩散训练方案,可适配边缘设备的多样化需求;随后基于具体量化要求研究了能效优化问题。数值结果表明,与基线联邦扩散方法和固定量化联邦扩散方法相比,所提方法在有效维持生成数据合理质量与多样性的同时,显著降低了系统能耗并减小了传输模型规模。

英文摘要:

Generative Artificial Intelligence (GAI) shows remarkable productivity and creativity in Mobile Edge Networks, such as the metaverse and the Industrial Internet of Things. Federated learning is a promising technique for effectively training GAI models in mobile edge networks due to its data distribution. However, there is a notable issue with communication consumption when training large GAI models like generative diffusion models in mobile edge networks. Additionally, the substantial energy consumption associated with training diffusion-based models, along with the limited resources of edge devices and complexities of network environments, pose challenges for improving the training efficiency of GAI models. To address this challenge, we propose an on-demand quantized energy-efficient federated diffusion approach for mobile edge networks. Specifically, we first design a dynamic quantized federated diffusion training scheme considering various demands from the edge devices. Then, we study an energy efficiency problem based on specific quantization requirements. Numerical results show that our proposed method significantly reduces system energy consumption and transmitted model size compared to both baseline federated diffusion and fixed quantized federated diffusion methods while effectively maintaining reasonable quality and diversity of generated data.

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。

↑