A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction
This incremental improvement addresses link prediction challenges in sparse, evolving networks like telecommunication records, benefiting network science applications.
The paper tackled the problem of link prediction in sparse, dynamic networks by improving Temporal Graph Networks (TGNs) with enclosing subgraphs to capture structural and temporal information, resulting in a 2.6% increase in average precision on a CDR dataset.
Predicting links in sparse, continuously evolving networks is a central challenge in network science. Conventional heuristic methods and deep learning models, including Graph Neural Networks (GNNs), are typically designed for static graphs and thus struggle to capture temporal dependencies. Snapshot-based techniques partially address this issue but often encounter data sparsity and class imbalance, particularly in networks with transient interactions such as telecommunication call detail records (CDRs). Temporal Graph Networks (TGNs) model dynamic graphs by updating node embeddings over time; however, their predictive accuracy under sparse conditions remains limited. In this study, we improve the TGN framework by extracting enclosing subgraphs around candidate links, enabling the model to jointly learn structural and temporal information. Experiments on a sparse CDR dataset show that our approach increases average precision by 2.6% over standard TGNs, demonstrating the advantages of integrating local topology for robust link prediction in dynamic networks.