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

TL;DR

TFWaveFormer introduces a novel Transformer architecture that combines temporal-frequency analysis with multi-resolution wavelet decomposition to improve dynamic link prediction by capturing complex multi-scale temporal patterns.

Contribution

The paper presents TFWaveFormer, a new model integrating spectral-temporal coordination and adaptive wavelet decomposition within a Transformer for enhanced dynamic link prediction.

Findings

Achieves state-of-the-art results on benchmark datasets.

Outperforms existing Transformer-based models significantly.

Effectively captures multi-scale temporal dynamics.

Abstract

Dynamic link prediction plays a crucial role in diverse applications including social network analysis, communication forecasting, and financial modeling. While recent Transformer-based approaches have demonstrated promising results in temporal graph learning, their performance remains limited when capturing complex multi-scale temporal dynamics. In this paper, we propose TFWaveFormer, a novel Transformer architecture that integrates temporal-frequency analysis with multi-resolution wavelet decomposition to enhance dynamic link prediction. Our framework comprises three key components: (i) a temporal-frequency coordination mechanism that jointly models temporal and spectral representations, (ii) a learnable multi-resolution wavelet decomposition module that adaptively extracts multi-scale temporal patterns through parallel convolutions, replacing traditional iterative wavelet transforms, and (iii) a hybrid Transformer module that effectively fuses local wavelet features with global temporal dependencies. Extensive experiments on benchmark datasets demonstrate that TFWaveFormer achieves state-of-the-art performance, outperforming existing Transformer-based and hybrid models by significant margins across multiple metrics. The superior performance of TFWaveFormer validates the effectiveness of combining temporal-frequency analysis with wavelet decomposition in capturing complex temporal dynamics for dynamic link prediction tasks.