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 2401.00631cs.NIcs.AIeess.SP
收藏

边缘AI即服务与协调深度神经网络

Edge AI as a Service with Coordinated Deep Neural Networks

Sharif University of Technology(谢里夫理工大学)

Alireza Maleki, Hamed Shah-Mansouri, Babak H. Khalaj

AI总结:

针对边缘AI服务中DNN协作不足的问题,提出CoDE算法,通过建立新推理路径协调DNN服务,实现推理吞吐量提升40%且准确率仅降2.3%。

摘要:

随着人工智能(AI)应用在下一代网络中的持续扩展,对深度神经网络(DNN)模型的需求日益增长。尽管部署在边缘的DNN模型有望以低延迟提供AI即服务,但其协作尚未被探索。在本文中,我们考虑DNN服务提供商共享其计算资源以及模型参数,并允许其他DNN在不镜像的情况下卸载其计算。我们提出了一种新颖的算法,称为边缘协调DNN(CoDE),通过建立新的推理路径来促进DNN服务之间的协调。CoDE旨在通过从单个模型创建多任务DNN来找到最优路径,即具有最高可能奖励的路径。该奖励反映了推理吞吐量和模型准确性。借助CoDE,DNN模型可以利用自身或其他模型的参数创建新的推理路径。然后,我们通过数值实验评估CoDE的性能。结果表明,推理吞吐量增加了40%,而平均准确率仅下降了2.3%。实验表明,与现有最先进方法相比,CoDE提高了推理吞吐量,并实现了更高的精度。

英文摘要:

As artificial intelligence (AI) applications continue to expand in next-generation networks, there is a growing need for deep neural network (DNN) models. Although DNN models deployed at the edge are promising for providing AI as a service with low latency, their cooperation is yet to be explored. In this paper, we consider that DNN service providers share their computing resources as well as their models' parameters and allow other DNNs to offload their computations without mirroring. We propose a novel algorithm called coordinated DNNs on edge (\textbf{CoDE}) that facilitates coordination among DNN services by establishing new inference paths. CoDE aims to find the optimal path, which is the path with the highest possible reward, by creating multi-task DNNs from individual models. The reward reflects the inference throughput and model accuracy. With CoDE, DNN models can make new paths for inference by using their own or other models' parameters. We then evaluate the performance of CoDE through numerical experiments. The results demonstrate a $40\%$ increase in the inference throughput while degrading the average accuracy by only $2.3\%$. Experiments show that CoDE enhances the inference throughput and, achieves higher precision compared to a state-of-the-art existing method.

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。

↑