Automated Model Design using Gated Neuron Selection in Telecom

TL;DR

This paper presents TabGNS, a gradient-based neural architecture search method tailored for tabular data in telecom, which automates model design, improves prediction accuracy, and significantly reduces model size and search time.

Contribution

Introduction of TabGNS, a novel NAS method for tabular data in telecommunications, enabling automated, efficient, and high-performance neural network design.

Findings

Improves prediction performance on telecom datasets

Reduces architecture size by up to 82%

Speeds up search time by up to 36 times

Abstract

The telecommunications industry is experiencing rapid growth in adopting deep learning for critical tasks such as traffic prediction, signal strength prediction, and quality of service optimisation. However, designing neural network architectures for these applications remains challenging and time-consuming, particularly when targeting compact models suitable for resource-constrained network environments. Therefore, there is a need for automating the model design process to create high-performing models efficiently. This paper introduces TabGNS (Tabular Gated Neuron Selection), a novel gradient-based Neural Architecture Search (NAS) method specifically tailored for tabular data in telecommunications networks. We evaluate TabGNS across multiple telecommunications and generic tabular datasets, demonstrating improvements in prediction performance while reducing the architecture size by 51-82% and reducing the search time by up to 36x compared to state-of-the-art tabular NAS methods. Integrating TabGNS into the model lifecycle management enables automated design of neural networks throughout the lifecycle, accelerating deployment of ML solutions in telecommunications networks.