TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction

Researchers propose TFWaveFormer, a novel Transformer architecture that combines temporal-frequency analysis with multi-resolution wavelet decomposition for dynamic link prediction. The framework achieves state-of-the-art performance on benchmark datasets by better capturing complex multi-scale temporal dynamics in applications like social networks and financial modeling.

• →TFWaveFormer integrates temporal-frequency analysis with wavelet decomposition to improve dynamic link prediction accuracy.
• →The architecture features three key components including temporal-frequency coordination and learnable multi-resolution wavelet decomposition.
• →The model outperforms existing Transformer-based and hybrid models by significant margins across multiple metrics.
• →Applications include social network analysis, communication forecasting, and financial modeling.
• →The research validates the effectiveness of combining temporal-frequency analysis with wavelet transforms for complex temporal dynamics.