Learning State-Augmented Policies for Information Routing in Communication Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Das, Sourajit, NaderiAlizadeh, Navid, Ribeiro, Alejandro
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929618813976576
author Das, Sourajit
NaderiAlizadeh, Navid
Ribeiro, Alejandro
author_facet Das, Sourajit
NaderiAlizadeh, Navid
Ribeiro, Alejandro
contents This paper examines the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information. We delineate a novel State Augmentation (SA) strategy to maximize the aggregate information at source nodes using graph neural network (GNN) architectures, by deploying graph convolutions over the topological links of the communication network. The proposed technique leverages only the local information available at each node and efficiently routes desired information to the destination nodes. We leverage an unsupervised learning procedure to convert the output of the GNN architecture to optimal information routing strategies. In the experiments, we perform the evaluation on real-time network topologies to validate our algorithms. Numerical simulations depict the improved performance of the proposed method in training a GNN parameterization as compared to baseline algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2310_00248
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning State-Augmented Policies for Information Routing in Communication Networks
Das, Sourajit
NaderiAlizadeh, Navid
Ribeiro, Alejandro
Networking and Internet Architecture
Machine Learning
Signal Processing
This paper examines the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information. We delineate a novel State Augmentation (SA) strategy to maximize the aggregate information at source nodes using graph neural network (GNN) architectures, by deploying graph convolutions over the topological links of the communication network. The proposed technique leverages only the local information available at each node and efficiently routes desired information to the destination nodes. We leverage an unsupervised learning procedure to convert the output of the GNN architecture to optimal information routing strategies. In the experiments, we perform the evaluation on real-time network topologies to validate our algorithms. Numerical simulations depict the improved performance of the proposed method in training a GNN parameterization as compared to baseline algorithms.
title Learning State-Augmented Policies for Information Routing in Communication Networks
topic Networking and Internet Architecture
Machine Learning
Signal Processing
url https://arxiv.org/abs/2310.00248