Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks

TL;DR

This paper introduces an unsupervised learning approach using Aggregation Graph Neural Networks for optimal resource allocation in asynchronous wireless networks, enabling local implementation and transferability without explicit model knowledge.

Contribution

The paper presents a novel unsupervised, policy-based method with permutation invariance for resource allocation in asynchronous wireless networks using Agg-GNNs.

Findings

The method performs well in numerical simulations.

It can be learned globally and asynchronously.

It demonstrates transferability of trained models.

Abstract

We consider optimal resource allocation problems under asynchronous wireless network setting. Without explicit model knowledge, we design an unsupervised learning method based on Aggregation Graph Neural Networks (Agg-GNNs). Depending on the localized aggregated information structure on each network node, the method can be learned globally and asynchronously while implemented locally. We capture the asynchrony by modeling the activation pattern as a characteristic of each node and train a policy-based resource allocation method. We also propose a permutation invariance property which indicates the transferability of the trained Agg-GNN. We finally verify our strategy by numerical simulations compared with baseline methods.