CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Hantong, Chen, Duxin, Yu, Wenwu
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