[论文解读] Transfer Learning for Future Wireless Networks: A Comprehensive Survey

Cong T. Nguyen, Nguyễn Văn Huynh+8 more|arXiv (Cornell University)|Feb 15, 2021

Wireless Signal Modulation Classification参考文献 166被引用 37

一句话总结

本文综述迁移学习（TL）如何通过利用相关任务的知识来提升无线网络中的机器学习（ML）在数据效率、学习速度、鲁棒性和隐私方面，特别是在5G/6G场景中。它涵盖TL的基础、分类以及TL在频谱管理、定位、信号识别、安全性、人体行为识别和缓存等领域的应用。

ABSTRACT

With outstanding features, Machine Learning (ML) has been the backbone of numerous applications in wireless networks. However, the conventional ML approaches have been facing many challenges in practical implementation, such as the lack of labeled data, the constantly changing wireless environments, the long training process, and the limited capacity of wireless devices. These challenges, if not addressed, will impede the effectiveness and applicability of ML in future wireless networks. To address these problems, Transfer Learning (TL) has recently emerged to be a very promising solution. The core idea of TL is to leverage and synthesize distilled knowledge from similar tasks as well as from valuable experiences accumulated from the past to facilitate the learning of new problems. Doing so, TL techniques can reduce the dependence on labeled data, improve the learning speed, and enhance the ML methods' robustness to different wireless environments. This article aims to provide a comprehensive survey on applications of TL in wireless networks. Particularly, we first provide an overview of TL including formal definitions, classification, and various types of TL techniques. We then discuss diverse TL approaches proposed to address emerging issues in wireless networks. The issues include spectrum management, localization, signal recognition, security, human activity recognition and caching, which are all important to next-generation networks such as 5G and beyond. Finally, we highlight important challenges, open issues, and future research directions of TL in future wireless networks.

研究动机与目标

• 动机：解决无线网络中的ML挑战（数据稀缺、动态环境、延迟、设备约束、隐私）。
• 调查TL基础、定义、分类，以及与无线网络相关的TL技术。
• 评述在关键无线领域的TL驱动方法（频谱管理、定位、信号识别、安全、人类活动识别、缓存）。
• 确定挑战、未解决问题以及未来无线网络中TL的研究方向。

提出的方法

• 给出领域、任务和TL的正式定义（源领域/目标领域和任务）。
• 将TL分成诱导式、传导式和无监督；并给出具体子类别（自学、多任务、领域自适应、协变量漂移等）。
• 描述TL技术：基于特征的、基于参数的、基于关系的、基于实例的迁移。
• 解释深度迁移学习（DTL）策略：现成的预训练模型、将预训练模型作为特征提取器，以及微调（权重初始化和选择性微调）。
• 讨论选择DTL策略的标准（数据可用性、领域相似性）。
• 总结无线网络中的TL挑战和未解问题，并提出未来研究方向。

实验结果

主要发现

• TL提供数据效率、学习速度加快、降低计算与通信开销，以及对无线ML系统的隐私保护。
• TL类别（诱导、传导、无监督）映射到不同的源/目标领域关系和标注条件。
• DTL策略使在无线任务中利用丰富的预训练模型进行特征提取或微调成为可能。
• 基于特征的和基于参数的TL方法可以缓解域偏移并提升在动态无线环境中的鲁棒性。
• 该综述突出在频谱管理、定位、信号识别、安全、活动识别和缓存等方面的广泛TL应用。