CoDCL combines counterfactual data augmentation with contrastive learning as a universal module to improve temporal link prediction in social networks.
Unifying evolution, explanation, and discernment: A generative approach for dynamic graph counterfactuals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks
CoDCL combines counterfactual data augmentation with contrastive learning as a universal module to improve temporal link prediction in social networks.