Structure of Deep Neural Networks with a Priori Information in Wireless Tasks

TL;DR

This paper introduces a structured deep neural network design for wireless tasks that leverages permutation invariance of a priori information, reducing parameters and training complexity while maintaining performance.

Contribution

The paper proposes a novel DNN structure with parameter sharing based on permutation invariance, specifically tailored for wireless applications, improving training efficiency.

Findings

Significant reduction in model parameters.

Lower training complexity demonstrated through simulations.

Effective learning of optimal policies in resource allocation.

Abstract

Deep neural networks (DNNs) have been employed for designing wireless networks in many aspects, such as transceiver optimization, resource allocation, and information prediction. Existing works either use fully-connected DNN or the DNNs with specific structures that are designed in other domains. In this paper, we show that a priori information widely existed in wireless tasks is permutation invariant. For these tasks, we propose a DNN with special structure, where the weight matrices between layers of the DNN only consist of two smaller sub-matrices. By such way of parameter sharing, the number of model parameters reduces, giving rise to low sample and computational complexity for training a DNN. We take predictive resource allocation as an example to show how the designed DNN can be applied for learning the optimal policy with unsupervised learning. Simulations results validate our analysis and show dramatic gain of the proposed structure in terms of reducing training complexity.