MLWiNS: Resource Constrained Mobile Data Analytics Assisted by the Wireless Edge

MLWiNS：无线边缘协助的资源受限移动数据分析

• 批准号: 2003182
• 负责人: Siddharth Garg
• 金额: $ 30万
• 依托单位: New York University
• 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: 2020-07-01 至 2024-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2003182&HistoricalAwards=false
• 关键词: MLWiNS; Resource; Constrained; Mobile; Data

Increasing amounts of data are being collected on mobile telephones and internet-of-things (IoT) devices. Users are interested in analyzing this data to extract actionable information, for example, identifying objects of interest from high-resolution mobile phone pictures. The state-of-the-art technique for such data analysis is via deep learning which makes use of sophisticated software algorithms modeled on the functioning of the human brain. Deep learning algorithms are, however, too complex to run on small, battery constrained mobile devices. The alternative, i.e., transmitting data to the mobile base station where the deep learning algorithm can be executed on a powerful server, consumes too much bandwidth. This project seeks to devise new methods to compress data before transmission, thus reducing bandwidth costs while still allowing for the data to be analyzed at the base station. Departing from existing data compression methods optimized for reproducing the original images, the project will use deep learning itself to compress the data in a fashion that only keeps the critical parts of data necessary for subsequent analysis. The resulting deep learning based compression algorithms will be simple enough to run on mobile devices while drastically reducing the amount of data that needs to be transmitted to mobile base stations for analysis, without significantly compromising the analysis performance. The proposed research will provide greater capability and functionality to mobile device users, enable extended battery lifetimes, and more efficient sharing of the wireless spectrum for analytics tasks. The project also envisions a multi-pronged effort aimed at outreach to communities of interest, educating and training the next generation of machine learning and wireless professionals at the K-12, undergraduate and graduate levels, and broadening participation of under-represented minority groups.The project seeks to learn “analytics-aware” compression schemes from data by training low-complexity compressor deep neural networks (DNNs) that execute on mobile devices and achieve a range of transmission rate and analytics accuracy targets. As a first step, efficient DNN pruning techniques will be developed to minimize the DNN complexity, while maintaining the rate-accuracy efficiency for one or a collection of analytics tasks. Next, to efficiently adapt to varying wireless channel conditions, the project will seek to design adaptive DNN architectures that can operate at variable transmission rates and computational complexities. For instance, when the wireless channel quality drops, the proposed compression scheme will be able to quickly reduce transmission rate in response while ensuring the same analytics accuracy, but at the cost of greater computational power on the mobile device. Further, wireless channel allocation and scheduling policies that leverage the proposed adaptive DNN architectures will be developed to optimize the overall analytics accuracy at the server. The benefits of the proposed approach in terms of total battery life savings for the mobile device will be demonstrated using detailed simulation studies of various wireless protocols including those used for LTE (Long Term Evolution) and mmWave channels.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.

越来越多的数据正在移动的电话和物联网（IoT）设备上收集。用户有兴趣分析这些数据以提取可操作的信息，例如，从高分辨率移动的手机图片中识别感兴趣的对象。这种数据分析的最先进技术是通过深度学习，它利用模拟人脑功能的复杂软件算法。然而，深度学习算法过于复杂，无法在小型电池受限的移动的设备上运行。另一种选择，即，将数据发送到移动的基站，其中深度学习算法可以在强大的服务器上执行，这消耗了太多的带宽。该项目旨在设计新的方法在传输前压缩数据，从而降低带宽成本，同时仍然允许在基站分析数据。与现有的数据压缩方法不同，该项目将使用深度学习本身来压缩数据，只保留后续分析所需的关键数据部分。由此产生的基于深度学习的压缩算法将足够简单，可以在移动的设备上运行，同时大幅减少需要传输到移动的基站进行分析的数据量，而不会显著影响分析性能。拟议的研究将为移动终端用户提供更大的能力和功能，延长电池寿命，并更有效地共享无线频谱以执行分析任务。该项目还设想了一项多管齐下的努力，旨在与感兴趣的社区进行外联，教育和培训K-12，本科和研究生级别的下一代机器学习和无线专业人员，该项目旨在通过训练低复杂度的压缩器深度神经网络（DNN），从数据中学习“分析感知”压缩方案。其在移动的设备上执行并实现一系列传输速率和分析准确性目标。作为第一步，将开发高效的DNN修剪技术，以最大限度地降低DNN复杂性，同时保持一个或一组分析任务的速率准确性效率。接下来，为了有效地适应不断变化的无线信道条件，该项目将寻求设计自适应DNN架构，这些架构可以以可变的传输速率和计算复杂度运行。例如，当无线信道质量下降时，所提出的压缩方案将能够作为响应快速降低传输速率，同时确保相同的分析准确性，但是以移动终端上的更大计算能力为代价。此外，将开发利用所提出的自适应DNN架构的无线信道分配和调度策略，以优化服务器的整体分析准确性。通过对各种无线协议（包括用于LTE（长期演进）和毫米波信道的无线协议）进行详细的仿真研究，将证明所提出的方法在节省移动终端的总电池寿命方面的优势。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值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

Single-Shot Compression for Hypothesis Testing

用于假设检验的单次压缩

• DOI: 10.1109/spawc51858.2021.9593264
• 发表时间: 2021
• 期刊: IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC
• 作者: Carpi, Fabrizio;Garg, Siddharth;Erkip, Elza
• 通讯作者: Erkip, Elza

Feature Compression for Rate Constrained Object Detection on the Edge

用于边缘速率受限对象检测的特征压缩

• 发表时间: 2022
• 期刊: In MLSys 2023 Workshop on Resource-Constrained Learning in Wireless Networks
• 作者: Yuan, Zhongzheng;Samyak Rawlekar;Siddharth Garg;Elza Erkip;Yao Wang
• 通讯作者: Yao Wang