CoDCL: Counterfactual Data Augmentation Contrastive Learning for Continuous-Time Dynamic Network Link Prediction
This work addresses the problem of improving prediction accuracy in dynamic networks for applications like social or communication systems, though it appears incremental as it builds on existing temporal graph models with a plug-and-play module.
The paper tackles the challenge of predicting links in dynamic networks with continuous-time structural evolution by proposing CoDCL, a framework that combines counterfactual data augmentation with contrastive learning to enhance model robustness, and experiments on real-world datasets show it significantly outperforms state-of-the-art baseline models.
The rapid growth and continuous structural evolution of dynamic networks make effective predictions increasingly challenging. To enable prediction models to adapt to complex temporal environments, they need to be robust to emerging structural changes. We propose a dynamic network learning framework CoDCL, which combines counterfactual data augmentation with contrastive learning to address this deficiency.Furthermore, we devise a comprehensive strategy to generate high-quality counterfactual data, combining a dynamic treatments design with efficient structural neighborhood exploration to quantify the temporal changes in interaction patterns.Crucially, the entire CoDCL is designed as a plug-and-play universal module that can be seamlessly integrated into various existing temporal graph models without requiring architectural modifications.Extensive experiments on multiple real-world datasets demonstrate that CoDCL significantly gains state-of-the-art baseline models in the field of dynamic networks, confirming the critical role of integrating counterfactual data augmentation into dynamic representation learning.