Automated Model Design using Gated Neuron Selection in Telecom

2026-02-11

AI Summary

This work addresses the inefficiency of manual neural architecture design in resource-constrained telecommunications scenarios. We propose TabGNS, a gradient-driven neural architecture search method tailored for tabular data, which introduces— for the first time—a gradient-guided gated neuron selection mechanism to automatically construct compact and efficient models. By leveraging gradient information to guide architectural decisions, TabGNS significantly improves search efficiency and model compression. Empirical evaluations on multiple telecommunications and general-purpose tabular datasets demonstrate that the method reduces model size by 51%–82% and accelerates the search process by up to 36×, all while maintaining or even enhancing predictive performance compared to existing approaches.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

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.

Problem

• Neural Architecture Search
• telecommunications
• tabular data
• model design automation
• resource-constrained environments

Innovation

• Neural Architecture Search
• Tabular Data
• Gated Neuron Selection
• Telecommunications
• Model Compression