arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.09483cs.LGcs.DCcs.ITeess.SPmath.ITstat.ML
收藏

一种面向物联网无线信道分布式函数压缩的机器学习框架

A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoT

Georgia Institute of Technology(佐治亚理工学院);Samsung Research America(三星美国研究院);Qualcomm Technologies, Inc.(高通技术公司)

Yashas Malur Saidutta, Afshin Abdi, Faramarz Fekri

AI总结:

针对物联网云端数据传输的网络压力问题,提出首个支持GMAC和正交AWGN信道的分布式函数压缩机器学习框架,无需传输原始数据,性能更优且通信量降两个数量级。

摘要:

物联网设备生成的海量数据与前沿机器学习技术将共同革新信息物理系统。在自动驾驶、增强现实等众多不同领域,分布式物联网设备需计算特定目标函数,而非仅执行障碍物检测、目标识别等简单任务。传统基于云端的方法侧重于将数据传输到中心节点进行训练或推理,给网络资源带来了巨大压力。为解决这一问题,据我们所知,我们开发了首个可在高斯多址信道(GMAC)和正交加性高斯白噪声(AWGN)信道上实现分布式函数压缩的机器学习框架。基于柯尔莫哥洛夫-阿诺德表示定理,我们的机器学习框架在设计上可为物联网中的目标函数压缩任务计算任意函数。重要的是,原始传感数据绝不会被传输到中心节点用于训练或推理,从而降低了通信量。我们为这些算法提供了理论收敛保证和通信量上界。仿真结果表明,所学习的函数压缩编码器和解码器性能显著优于传统方法,对信道条件变化和传感器故障具有鲁棒性。与基于云端的方案相比,我们的算法将信道使用量降低了两个数量级。

英文摘要:

IoT devices generating enormous data and state-of-the-art machine learning techniques together will revolutionize cyber-physical systems. In many diverse fields, from autonomous driving to augmented reality, distributed IoT devices compute specific target functions without simple forms like obstacle detection, object recognition, etc. Traditional cloud-based methods that focus on transferring data to a central location either for training or inference place enormous strain on network resources. To address this, we develop, to the best of our knowledge, the first machine learning framework for distributed functional compression over both the Gaussian Multiple Access Channel (GMAC) and orthogonal AWGN channels. Due to the Kolmogorov-Arnold representation theorem, our machine learning framework can, by design, compute any arbitrary function for the desired functional compression task in IoT. Importantly the raw sensory data are never transferred to a central node for training or inference, thus reducing communication. For these algorithms, we provide theoretical convergence guarantees and upper bounds on communication. Our simulations show that the learned encoders and decoders for functional compression perform significantly better than traditional approaches, are robust to channel condition changes and sensor outages. Compared to the cloud-based scenario, our algorithms reduce channel use by two orders of magnitude.

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。

↑