Lightweight Continuous-Time Graph Learning for Spectrum Prediction in 6G Networks

In the era of 6G and dynamic spectrum access, the exponential growth of connected devices and diverse service demands intensifies spectrum scarcity and interference. Reliable spectrum prediction is thus essential to enable proactive access, alleviate congestion, and enhance spectral efficiency. Existing approaches suffer from a trade-off between accuracy and efficiency: model-driven methods often fail to capture inter-dimensional correlations, whereas data-driven methods achieve higher accuracy at the cost of excessive computational complexity. To address these challenges, we propose a lightweight spectrum prediction framework that integrates patch-based local feature extraction, sparse graph attention for efficient global dependency modeling, positional reconstruction for time–frequency alignment, and a closed-form continuous-time prediction network for accurate temporal forecasting. Simulation results demonstrate that the proposed method reduces the root mean square error by 2.7%~65% while lowering computational resource consumption by 19%~84% compared with state-of-the-art baselines. These results underline the potential of the proposed approach to support scalable spectrum management in 6G wireless networks, thereby facilitating ultra-reliable low-latency communication, massive IoT connectivity, and intelligent spectrum sharing.