CRII: SHF Software and Hardware Architecture Co-Design for Deep Learning on Mobile Device

CRII：移动设备深度学习的SHF软硬件架构协同设计

• 批准号: 1850045
• 负责人: Cong Wang
• 金额: $ 17.5万
• 依托单位: Old Dominion University Research Foundation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-15 至 2022-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1850045&HistoricalAwards=false
• 关键词: CRII; SHF; Software; Hardware; Architecture

Smartphones have become an indispensable part of our lives, acting as the primary tool for many essential functions. A smartphone carries a rich set of data with all kinds of personal information. Powered by machine learning, mobile applications are utilizing these data for better quality of service. Current practice requires users to offload computation tasks to the cloud with incumbent challenges on privacy, performance and user experience fronts. Boosted by the dramatic increase in mobile processing power, this project seeks to bring machine intelligence to mobile devices. The results are expected to inspire both theoretical and system research in the areas of software foundations for embedded machine intelligence. Lessons learned through this project will be fundamentally important in the designs of the next generation mobile operating system and hardware architecture. The results will be disseminated through publications and talks. This project seeks to develop a high-performance, privacy-preserving and energy-efficient mobile-based platform, with an application of behavioral authentication. The research will study the optimal representation of sensing data and develop a compact and powerful neural network architecture. All computation including both inference and training will be performed on the mobile device. A protocol to enable feature transfer between the mobile and the cloud will be developed to reduce overfitting and speed up model convergence, along with a new training algorithm to exploit cache locality and mitigate the memory bottleneck. The optimal combinations of batch size and learning rate will be explored within memory constraints and accuracy requirements to minimize training time. The problem of when and how training should be scheduled on a mobile device will be investigated by considering low-level operation with high-level user interaction to achieve a good balance between performance and resource consumption. All these modules will be integrated and implemented in Android and evaluated on various smartphone models.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.

智能手机已经成为我们生活中不可或缺的一部分，成为许多基本功能的主要工具。智能手机携带着一组丰富的数据，其中包含各种个人信息。在机器学习的支持下，移动应用程序正在利用这些数据来提高服务质量。当前的做法要求用户将计算任务卸载到云上，同时面临隐私、性能和用户体验方面的挑战。在移动处理能力大幅提高的推动下，该项目寻求将机器智能引入移动设备。这一结果有望激励嵌入式机器智能软件基础领域的理论和系统研究。从这个项目中学到的经验教训将在下一代移动操作系统和硬件架构的设计中起到至关重要的作用。结果将通过出版物和讲座传播。该项目旨在开发一个高性能、隐私保护和节能的基于移动的平台，并应用行为认证。这项研究将研究传感数据的最佳表示，并开发出紧凑而强大的神经网络结构。包括推理和训练在内的所有计算都将在移动设备上执行。将开发一种协议，以实现移动设备和云设备之间的特征传输，以减少过度拟合并加快模型收敛，并将开发一种新的训练算法，以利用缓存局部性和缓解内存瓶颈。将在记忆限制和精度要求的范围内探索批次大小和学习率的最佳组合，以最大限度地减少训练时间。应在何时以及如何在移动设备上安排培训的问题将通过考虑具有高级用户交互的低级别操作来调查，以实现性能和资源消耗之间的良好平衡。所有这些模块都将在Android中集成和实施，并在各种智能手机型号上进行评估。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Explore Truthful Incentives for Tasks with Heterogenous Levels of Difficulty in the Sharing Economy

• DOI: 10.24963/ijcai.2019/94
• 发表时间: 2019-08
• 作者: Pengzhan Zhou;Xin Wei;Cong Wang;Yuanyuan Yang

Towards Efficient Scheduling of Federated Mobile Devices Under Computational and Statistical Heterogeneity

• DOI: 10.1109/tpds.2020.3023905
• 发表时间: 2020-05
• 期刊: IEEE Transactions on Parallel and Distributed Systems
• 影响因子: 5.3
• 作者: Cong Wang;Yuanyuan Yang;Pengzhan Zhou

Evade Deep Image Retrieval by Stashing Private Images in the Hash Space

• DOI: 10.1109/cvpr42600.2020.00967
• 发表时间: 2020-06
• 期刊: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Y. Xiao;Cong Wang;Xing Gao

Close the Gap between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop

• DOI: 10.1145/3343031.3350904
• 发表时间: 2019-10
• 期刊: Proceedings of the 27th ACM International Conference on Multimedia
• 作者: Cong Wang;Y. Xiao;Xing Gao;Li Li-Li;Jun Wang

A Framework for Behavioral Biometric Authentication Using Deep Metric Learning on Mobile Devices

• DOI: 10.1109/tmc.2021.3072608
• 发表时间: 2020-05
• 期刊: IEEE Transactions on Mobile Computing
• 影响因子: 7.9
• 作者: Cong Wang;Y. Xiao;Xing Gao;Li Li-Li;Jun Wang