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

2026-03-04

AI Summary

Dynamic link prediction faces significant challenges in modeling complex, multi-scale temporal dynamics. This work proposes a novel hybrid Transformer architecture that integrates time-frequency analysis with learnable multi-resolution wavelet decomposition. By introducing a time-frequency cooperative mechanism, the model adaptively captures both local wavelet features and global temporal dependencies, effectively representing multi-scale dynamic patterns. Departing from conventional iterative wavelet transforms, the approach incorporates a learnable wavelet module and parallel convolutional structures to enhance expressiveness and efficiency. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method substantially outperforms existing Transformer-based and hybrid models, achieving state-of-the-art performance in dynamic link prediction.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• dynamic link prediction
• temporal dynamics
• multi-scale modeling
• temporal graph learning
• time-series analysis

Innovation

• Temporal-Frequency Collaboration
• Multi-resolution Wavelet Decomposition
• Dynamic Link Prediction
• Wavelet Transformer
• Time-series Graph Learning