Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey

TL;DR

This survey reviews how multi-modal foundation models are being integrated into wireless networks to enhance prediction and control tasks, highlighting datasets, methodologies, challenges, and future research directions.

Contribution

It provides a comprehensive overview of the application of multi-modal foundation models in wireless network management, including development datasets and methodologies.

Findings

Multi-modal FMs improve understanding of wireless network context.

FMs enable advanced prediction and control in wireless systems.

Discussion of challenges and future directions in FM-enhanced wireless networks.

Abstract

Foundation models (FMs) are recognized as a transformative breakthrough that has started to reshape the future of artificial intelligence (AI) across both academia and industry. The integration of FMs into wireless networks is expected to enable the development of general-purpose AI agents capable of handling diverse network management requests and highly complex wireless-related tasks involving multi-modal data. Inspired by these ideas, this work discusses the utilization of FMs, especially multi-modal FMs in wireless networks. We focus on two important types of tasks in wireless network management: prediction tasks and control tasks. In particular, we first discuss FMs-enabled multi-modal contextual information understanding in wireless networks. Then, we explain how FMs can be applied to prediction and control tasks, respectively. Following this, we introduce the development of wireless-specific FMs from two perspectives: available datasets for development and the methodologies used. Finally, we conclude with a discussion of the challenges and future directions for FM-enhanced wireless networks.