Improving Learning Efficiency for Wireless Resource Allocation with Symmetric Prior

TL;DR

This paper demonstrates that leveraging symmetric prior knowledge, specifically permutation equivariance, significantly enhances the learning efficiency of deep neural networks in wireless resource allocation tasks, reducing training data and time.

Contribution

It introduces a novel approach of exploiting permutation equivariance as a symmetric prior to improve deep learning efficiency in wireless communications.

Findings

Training samples needed are reduced by up to 2,400 times.

Learning efficiency improves across multiple wireless tasks.

Training time and parameters are significantly decreased.

Abstract

Improving learning efficiency is paramount for learning resource allocation with deep neural networks (DNNs) in wireless communications over highly dynamic environments. Incorporating domain knowledge into learning is a promising way of dealing with this issue, which is an emerging topic in the wireless community. In this article, we first briefly summarize two classes of approaches to using domain knowledge: introducing mathematical models or prior knowledge to deep learning. Then, we consider a kind of symmetric prior, permutation equivariance, which widely exists in wireless tasks. To explain how such a generic prior is harnessed to improve learning efficiency, we resort to ranking, which jointly sorts the input and output of a DNN. We use power allocation among subcarriers, probabilistic content caching, and interference coordination to illustrate the improvement of learning efficiency by exploiting the property. From the case study, we find that the required training samples to achieve given system performance decreases with the number of subcarriers or contents, owing to an interesting phenomenon: "sample hardening". Simulation results show that the training samples, the free parameters in DNNs and the training time can be reduced dramatically by harnessing the prior knowledge. The samples required to train a DNN after ranking can be reduced by $15 \sim 2,400$ folds to achieve the same system performance as the counterpart without using prior.