边端协同微调大模型，显著降低延迟与能耗
Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks
- 将大模型分片部署在移动端与边缘服务器间交替计算
- 训练延迟平均降低70.8%，服务器能耗减少53.1%
- 适合资源异构的边缘网络场景，尤其关注能效的移动应用
本文提出一种面向边缘网络中使用地理分布个人数据微调大语言模型的节能分割学习框架，将大语言模型分片并在大量移动设备与边缘服务器间交替计算。针对边缘网络中设备异构性与信道动态变化问题，设计了剪切层与计算资源决策（CARD）算法，以最小化训练延迟和能耗。仿真结果表明，相比基准方法，所提方案可使平均训练延迟降低70.8%，边缘服务器能耗减少53.1%。
原文摘要 · Abstract (English)
In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile devices and an edge server. Considering the device heterogeneity and channel dynamics in edge networks, a \underline{C}ut l\underline{A}yer and computing \underline{R}esource \underline{D}ecision (CARD) algorithm is developed to minimize training delay and energy consumption. Simulation results demonstrate that the proposed approach reduces the average training delay and server's energy consumption by 70.8% and 53.1%, compared to the benchmarks, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。