DNRHP: Temporal Network Representation Learning via Hawkes Point Process.

Abstract

Graph neural networks (GNNs) have significantly advanced our ability to mine structured data, playing a central role in areas such as social networks and recommendation systems. However, while most GNN-based methods focus on learning node representations in static graphs, they often ignore the dynamic nature of real-world networks, limiting their applicability. Furthermore, existing dynamic representation learning methods using Hawkes point processes, while capable of modeling event sequences, are inherently transductive and tailored to specific scenarios with dual timescales and mixed event types, thus not fully generalizable. To bridge this gap, we introduce DNRHP, a novel framework for learning temporal network representations. Specifically, DNRHP integrates historical edge (HE) information with the network's evolutionary properties, using the Hawkes point process to model edge formation. It captures not only the influence of past events on the likelihood of future connections but also the impact of the structural evolution of the network. The novelty of our model lies in its comprehensive consideration of the dynamics of network evolution and historical connectivity, allowing for a more accurate representation of nodes and their interactions over time. Extensive experiments on diverse real-world networks demonstrate the effectiveness of DNRHP, outperforming state-of-the-art baselines in terms of accuracy and efficiency for tasks such as node classification and link prediction.