DyGnROLE: Modeling Asymmetry in Dynamic Graphs with Node-Role-Oriented Latent Encoding

Researchers introduce DyGnROLE, a new AI architecture that better models directed dynamic graphs by treating source and destination nodes differently. The system uses role-specific embeddings and a self-supervised learning approach called Temporal Contrastive Link Prediction to achieve superior performance on future edge classification tasks.

• →DyGnROLE addresses limitations in existing dynamic graph models that use shared parameters for both source and destination nodes.
• →The architecture employs separate embedding vocabularies and role-semantic positional encodings to capture distinct node behaviors.
• →A new self-supervised pretraining method called Temporal Contrastive Link Prediction enables learning without labeled data.
• →The model substantially outperforms state-of-the-art baselines on future edge classification benchmarks.
• →Role-aware modeling is established as an effective strategy for improving dynamic graph learning systems.