CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918490306248704 |
|---|---|
| author | Feng, Hantong Chen, Duxin Yu, Wenwu |
| author_facet | Feng, Hantong Chen, Duxin Yu, Wenwu |
| contents | Temporal link prediction is crucial for rapidly growing social networks. Existing methods often overlook the underlying causal mechanisms that drive link formation, making it difficult for algorithms to adapt to complex structures that continuously evolve over time. 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-inspired 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 conducted on multiple real-world datasets demonstrate that CoDCL significantly outperforms state-of-the-art baselines in temporal link prediction, highlighting the effectiveness of integrating counterfactual-inspired data augmentation into dynamic representation learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22427 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks Feng, Hantong Chen, Duxin Yu, Wenwu Machine Learning Artificial Intelligence Temporal link prediction is crucial for rapidly growing social networks. Existing methods often overlook the underlying causal mechanisms that drive link formation, making it difficult for algorithms to adapt to complex structures that continuously evolve over time. 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-inspired 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 conducted on multiple real-world datasets demonstrate that CoDCL significantly outperforms state-of-the-art baselines in temporal link prediction, highlighting the effectiveness of integrating counterfactual-inspired data augmentation into dynamic representation learning. |
| title | CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.22427 |