Collaborative Research: MLWiNS: Deep Neural Networks Meet Physical Layer Communications -- Learning with Knowledge of Structure

合作研究：MLWiNS：深度神经网络满足物理层通信——利用结构知识进行学习

• 批准号: 2002908
• 负责人: Lizhong Zheng
• 金额: $ 26.99万
• 依托单位: Massachusetts Institute of Technology
• 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: 2020-08-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2002908&HistoricalAwards=false
• 关键词: Collaborative; Research; MLWiNS; Deep; Neural

Machine learning techniques are expected to be the main driving force for performance gains in future wireless networks. In practice, the difficulty in applying learning algorithms in communication systems comes from a paradigm shift in the methodology: From conventional model-based analytical solutions to data-driven empirical-result-based approaches. While learning algorithms offer better flexibility and efficiency in using computational resources, the lack of guarantees in the performance, robustness and security raise issues when adopting into engineering designs. The goal of this project is to combine learning-based data-driven approaches with conventional model-based analysis, to design novel learning algorithms that can utilize the structural knowledge of engineering systems, thus reaping the advantages of both methods.This project focuses on the physical layer of wireless networks, where analytical solutions, clearly defined performance benchmarks, as well as clearly isolated modeling deficiencies are usually present. They key challenge is to utilize the analytical results whenever possible, and focus the learning power on those parts of the system where the conventional approach fails, including non-linear, non-Gaussian, and non-stationary elements. Three problem areas are identified to test such new hybrid design methods, including 1) symbol-detection for MIMO fading interference channels, 2) massive MIMO with low resolution analog-to-digital converters, and 3) MIMO-OFDM waveform analysis in non-linear radio 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.

机器学习技术预计将成为未来无线网络性能提升的主要驱动力。在实践中，在通信系统中应用学习算法的困难来自于方法论的范式转变：从传统的基于模型的分析解决方案到数据驱动的基于经验结果的方法。虽然学习算法在使用计算资源方面提供了更好的灵活性和效率，但在性能、鲁棒性和安全性方面缺乏保证，在工程设计中采用时会出现问题。该项目的目标是将基于学习的数据驱动方法与传统的基于模型的分析相结合，设计能够利用工程系统结构知识的新颖学习算法，从而获得两种方法的优点。该项目重点关注无线网络的物理层，其中通常存在分析解决方案、明确定义的性能基准以及明确隔离的建模缺陷。他们面临的主要挑战是尽可能利用分析结果，并将学习能力集中在传统方法失败的系统部分，包括非线性、非高斯和非平稳元素。 确定了三个问题领域来测试这种新的混合设计方法，包括 1) MIMO 衰落干扰信道的符号检测，2) 具有低分辨率模数转换器的大规模 MIMO，以及 3) 非线性无线电信道中的 MIMO-OFDM 波形分析。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进行评估，被认为值得支持 标准。

项目成果

On Semi-Supervised Estimation of Distributions

• DOI: 10.1109/isit54713.2023.10206752
• 发表时间: 2023-05
• 期刊: 2023 IEEE International Symposium on Information Theory (ISIT)
• 作者: H. Erol;Erixhen Sula;Lizhong Zheng

Kernel Subspace and Feature Extraction

• DOI: 10.1109/isit54713.2023.10206532
• 发表时间: 2023-01
• 期刊: 2023 IEEE International Symposium on Information Theory (ISIT)
• 作者: Xiangxiang Xu;Lizhong Zheng

Channel Equalization Through Reservoir Computing: A Theoretical Perspective

通过储层计算实现通道均衡：理论视角

• DOI: 10.1109/lwc.2023.3234239
• 发表时间: 2023
• 期刊: IEEE Wireless Communications Letters
• 影响因子: 6.3
• 作者: Jere, Shashank;Safavinejad, Ramin;Zheng, Lizhong;Liu, Lingjia
• 通讯作者: Liu, Lingjia

RC-Struct: A Structure-Based Neural Network Approach for MIMO-OFDM Detection

RC-Struct：一种用于 MIMO-OFDM 检测的基于结构的神经网络方法

• DOI: 10.1109/twc.2022.3155945
• 发表时间: 2022
• 期刊: IEEE Transactions on Wireless Communications
• 影响因子: 10.4
• 作者: Xu, Jiarui;Zhou, Zhou;Li, Lianjun;Zheng, Lizhong;Liu, Lingjia
• 通讯作者: Liu, Lingjia