arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13206cs.NI
收藏

迈向移动边缘网络中大人工智能模型资源高效协作

Toward Resource-Efficient Collaboration of Large AI Models in Mobile Edge Networks

University of Macau(澳门大学);Zhejiang University of Technology(浙江工业大学);Nanyang Technological University(南洋理工大学);Auburn University(奥本大学)

Peichun Li, Liping Qian, Dusit Niyato, Shiwen Mao, Yuan Wu

AI总结:

本文提出了一种多阶段扩散框架,用于在移动边缘网络中实现大AI模型的资源高效协作,提升数据生成的效率和适应性。

摘要:

在移动边缘网络中,大人工智能(AI)模型的协作已成为满足网络边缘日益增长的智能服务需求的一种有前景的范式。通过使多个设备能够协同执行子模型或子任务,协同AI在受限资源下提高了推理效率和服务质量。然而,在此类环境中部署大型AI模型仍然具有挑战性,因为模型复杂性与边缘网络中有限的计算、内存和通信资源之间存在固有的不匹配。本文提供了移动边缘网络中协同AI系统架构的全面概述,以及在交通和医疗领域中的代表性应用场景。我们进一步介绍了近年来在资源高效协作技术方面的最新进展,将其分为空间和时间两类方法。主要的空间方法包括联邦调优、专家混合、基于补丁的扩散和分层扩散。同时,重要的时间方法包括拆分学习、级联推理、推测解码和路由推理。在此基础上,我们提出了一种多阶段扩散框架,使大型生成模型能够弹性地分布在异构边缘资源上。实验结果表明,我们的框架在数据生成的效率和适应性方面均实现了性能提升。

英文摘要:

The collaboration of large artificial intelligence (AI) models in mobile edge networks has emerged as a promising paradigm to meet the growing demand for intelligent services at the network edge. By enabling multiple devices to cooperatively execute submodels or subtasks, collaborative AI enhances inference efficiency and service quality with constrained resources. However, deploying large AI models in such environments remains challenging due to the intrinsic mismatch between model complexity and the limited computation, memory, and communication resources in edge networks. This article provides a comprehensive overview of the system architecture for collaborative AI in mobile edge networks, along with representative application scenarios in transportation and healthcare. We further present recent advances in resource-efficient collaboration techniques, categorized into spatial and temporal approaches. The major spatial approaches include federated tuning, mixture of experts, patch-based diffusion, and hierarchical diffusion. Meanwhile, the important temporal approaches encompass split learning, cascading inference, speculative decoding, and routing inference. Building upon these foundations, we propose a multi-stage diffusion framework that enables elastic distribution of large generative models across heterogeneous edge resources. Experimental results demonstrate that our framework achieves performance improvement in both efficiency and adaptability for data generation.

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。

↑