权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Collaborative Research: CNS Core: Small: Towards Automated and QoE-driven Machine Learning Model Selection for Edge Inference

合作研究：CNS 核心：小型：面向边缘推理的自动化和 QoE 驱动的机器学习模型选择

基本信息

批准号：
2007115
负责人：
Shaolei Ren
金额：
$ 24.99万
依托单位：
University of California-Riverside
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-10-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2007115&HistoricalAwards=false
关键词：
Collaborative Research CNS Core Small

项目摘要

Edge devices, such as mobile phones, drones and robots, have been emerging as an increasingly more important platform for deep neural network (DNN) inference. For an edge device, selecting an optimal DNN model out of many possibilities is crucial for maximizing the user’s quality of experience (QoE), but this is significantly challenged by the high degree of heterogeneity in edge devices and constant-changing usage scenarios. The current practice commonly selects a single DNN model for many or all edge devices, which can only provide a satisfactory QoE for a small fraction of users at best. Alternatively, device-specific DNN model optimization is time-consuming and not scalable to a large diversity of edge devices. Moreover, the existing approaches focus on optimizing a certain objective metric for edge inference, which may not translate into improvement of the actual QoE for users. By leveraging the predictive power of machine learning and keeping users in a loop, this project proposes an automated and scalable device-level DNN model selection engine for QoE-optimal edge inference. Specifically, this project includes two thrusts: first, it exploits online learning to predict QoE for each edge device, automating deployment-stage DNN model selection; and second, it builds a runtime QoE predictor and automatically selects an optimal DNN model given runtime contextual information.This project represents an important departure from and an essential complement to the current practices in DNN model optimization. It can bring the benefits of DNN-enabled intelligence to many more resource-constrained edge devices with an optimal QoE. Additionally, it provides novel observations, insights and principles for edge inference, catalyzing the transformation of the design of DNN models into a new user-centric paradigm. This project also enables new opportunities to improve curriculum design and attract students, especially under-represented minorities, to engage in science, technology, engineering, and mathematics fields.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

手机、无人机和机器人等边缘设备已成为深度神经网络 (DNN) 推理日益重要的平台。对于边缘设备而言，从多种可能性中选择最佳的 DNN 模型对于最大化用户体验质量 (QoE) 至关重要，但这受到边缘设备高度异构性和不断变化的使用场景的巨大挑战。目前的实践通常为许多或所有边缘设备选择单一的 DNN 模型，这最多只能为一小部分用户提供令人满意的 QoE。另外，特定于设备的 DNN 模型优化非常耗时，并且无法扩展到多种边缘设备。此外，现有方法侧重于优化边缘推理的某个客观指标，这可能无法转化为用户实际 QoE 的改善。通过利用机器学习的预测能力并使用户处于循环状态，该项目提出了一种自动化且可扩展的设备级 DNN 模型选择引擎，用于 QoE 最佳边缘推理。具体来说，该项目包括两个重点：首先，它利用在线学习来预测每个边缘设备的 QoE，自动化部署阶段的 DNN 模型选择；其次，它构建了一个运行时 QoE 预测器，并在给定运行时上下文信息的情况下自动选择最佳 DNN 模型。该项目代表了对当前 DNN 模型优化实践的重要背离和重要补充。它可以为更多资源受限的边缘设备带来支持 DNN 的智能的优势，并提供最佳的 QoE。此外，它还为边缘推理提供了新颖的观察、见解和原理，促进了 DNN 模型设计向新的以用户为中心的范式的转变。该项目还提供了新的机会来改进课程设计并吸引学生，特别是代表性不足的少数族裔，参与科学、技术、工程和数学领域。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。