SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling

TL;DR

SpectrumFM introduces a foundation model for spectrum cognition that leverages advanced neural architectures and self-supervised learning to significantly improve performance across diverse spectrum tasks.

Contribution

The paper presents SpectrumFM, a novel spectrum foundation model with a specialized encoder, self-supervised pre-training tasks, and efficient fine-tuning, enabling superior generalization and accuracy in spectrum cognition.

Findings

30% improvement in detection probability at -4 dB SNR for spectrum sensing

Over 10% increase in AUC for anomaly detection

9.6% higher accuracy in wireless technology classification

Abstract

The enhancement of spectrum efficiency and the realization of secure spectrum utilization are critically dependent on spectrum cognition. However, existing spectrum cognition methods often exhibit limited generalization and suboptimal accuracy when deployed across diverse spectrum environments and tasks. To overcome these challenges, we propose a spectrum foundation model, termed SpectrumFM, which provides a new paradigm for spectrum cognition. An innovative spectrum encoder that exploits the convolutional neural networks and the multi-head self attention mechanisms is proposed to effectively capture both fine-grained local signal structures and high-level global dependencies in the spectrum data. To enhance its adaptability, two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, are developed for pre-training SpectrumFM, enabling the model to learn rich and transferable representations. Furthermore, low-rank adaptation (LoRA) parameter-efficient fine-tuning is exploited to enable SpectrumFM to seamlessly adapt to various downstream spectrum cognition tasks, including spectrum sensing (SS), anomaly detection (AD), and wireless technology classification (WTC). Extensive experiments demonstrate the superiority of SpectrumFM over state-of-the-art methods. Specifically, it improves detection probability in the SS task by 30% at -4 dB signal-to-noise ratio (SNR), boosts the area under the curve (AUC) in the AD task by over 10%, and enhances WTC accuracy by 9.6%.