arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.01793cs.LGeess.SP
收藏

CacheNet:一个用于边缘深度学习推理的模型缓存框架

CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge

McMaster University(麦克马斯特大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))

Yihao Fang, Shervin Manzuri Shalmani, Rong Zheng

摘要:

深度神经网络(DNN)在机器感知应用(如图像分类和语音识别)中的成功是以高计算和存储复杂度为代价的。未压缩的大规模DNN模型的推理只能在云中运行,云和终端设备之间来回存在额外的通信延迟,而压缩的DNN模型以较低的预测准确度为代价在终端设备上实现实时推理。为了两全其美(延迟和准确性),我们提出了CacheNet,一个模型缓存框架。CacheNet在终端设备上缓存低复杂度模型,在边缘或云服务器上缓存高复杂度(或完整)模型。通过利用流数据中的时间局部性,可以实现高缓存命中和因此更短的延迟,而预测准确性没有降低或仅略有降低。在CIFAR-10和FVG上的实验表明,CacheNet比仅在终端设备或边缘服务器上运行推理任务的基准方法快58-217%。

英文摘要:

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models can only run in the cloud with extra communication latency back and forth between cloud and end devices, while compressed DNN models achieve real-time inference on end devices at the price of lower predictive accuracy. In order to have the best of both worlds (latency and accuracy), we propose CacheNet, a model caching framework. CacheNet caches low-complexity models on end devices and high-complexity (or full) models on edge or cloud servers. By exploiting temporal locality in streaming data, high cache hit and consequently shorter latency can be achieved with no or only marginal decrease in prediction accuracy. Experiments on CIFAR-10 and FVG have shown CacheNet is 58-217% faster than baseline approaches that run inference tasks on end devices or edge servers alone.

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。

↑