Towards Neural Architecture Search for Transfer Learning in 6G Networks

TL;DR

This paper reviews how Neural Architecture Search and Transfer Learning can be integrated for optimizing AI models in future 6G networks, addressing challenges like multi-objective search and data heterogeneity.

Contribution

It provides a comprehensive review of NAS and TL in networking, identifies key open challenges, and proposes future research directions for 6G AI-native networks.

Findings

Identifies combining NAS and TL as a key future direction.

Highlights the importance of multi-objective search in 6G.

Discusses the unique challenges of tabular data in network models.

Abstract

The future 6G network is envisioned to be AI-native, and as such, ML models will be pervasive in support of optimizing performance, reducing energy consumption, and in coping with increasing complexity and heterogeneity. A key challenge is automating the process of finding optimal model architectures satisfying stringent requirements stemming from varying tasks, dynamicity and available resources in the infrastructure and deployment positions. In this paper, we describe and review the state-of-the-art in Neural Architecture Search and Transfer Learning and their applicability in networking. Further, we identify open research challenges and set directions with a specific focus on three main requirements with elements unique to the future network, namely combining NAS and TL, multi-objective search, and tabular data. Finally, we outline and discuss both near-term and long-term work ahead.