To Supervise or Not to Supervise: How to Effectively Learn Wireless Interference Management Models?
To Supervise or Not to Supervise: How to Effectively Learn Wireless Interference Management Models?
复制标题
DOI：
10.1109/spawc51858.2021.9593184
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Bingqing Song;Haoran Sun;Wenqiang Pu;Sijia Liu;Mingyi Hong
中科院分区：
文献类型：
--
作者：
Bingqing Song;Haoran Sun;Wenqiang Pu;Sijia Liu;Mingyi Hong
机器学习已成功解决无线干扰管理问题。不同类型的深度神经网络（DNN）已经被训练来完成关键任务，如功率控制，波束成形和准入控制。有两种最先进的方法来训练这种基于DNN的干扰管理模型：监督学习（即，拟合由优化算法生成的标签）和无监督学习（即，直接优化某些系统性能测量）。然而，在实践中，哪种方法更有效并不清楚。本文对这两种训练方法进行了理论和实验研究。首先，我们展示了一个有点令人惊讶的结果，对于一些特殊的功率控制问题，无监督学习的表现可能比它的对手差得多，因为它更有可能陷入一些低质量的局部解决方案。然后，我们提供了一系列的理论结果，以进一步了解这两种方法的属性。据我们所知，这是第一组理论成果，试图了解不同的训练方法，在基于学习的无线通信系统的设计。
Machine learning has become successful in solving wireless interference management problems. Different kinds of deep neural networks (DNNs) have been trained to accomplish key tasks such as power control, beamforming and admission control. There are two state-of-the-art approaches to train such DNNs based interference management models: supervised learning (i.e., fits labels generated by an optimization algorithm) and unsupervised learning (i.e., directly optimizes some system performance measure). However, it is by no means clear which approach is more effective in practice. In this paper, we conduct some theory and experiment study about these two training approaches. First, we show a somewhat surprising result, that for some special power control problem, the unsupervised learning can perform much worse than its counterpart, because it is more likely to get stuck at some low-quality local solutions. We then provide a series of theoretical results to further understand the properties of the two approaches. To our knowledge, these are the first set of theoretical results trying to understand different training approaches in learning-based wireless communication system design.