Deep Graph Neural Point Process For Learning Temporal Interactive Networks

TL;DR

This paper introduces DGNPP, a novel deep graph neural point process model that effectively captures network topology and temporal dynamics for improved prediction in temporal interaction networks.

Contribution

The paper proposes DGNPP, integrating static topological features and dynamic temporal updates, advancing the modeling of temporal interaction networks beyond prior methods.

Findings

DGNPP outperforms baseline models in event and time prediction tasks.

The model effectively captures network topology and temporal dynamics.

Experimental results show high efficiency and superior accuracy.

Abstract

Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point Process(DGNPP) model for TIN is proposed. DGNPP consists of two key modules: the Node Aggregation Layer and the Self Attentive Layer. The Node Aggregation Layer captures topological structures to generate static representation for users and items, while the Self Attentive Layer dynamically updates embeddings over time. By incorporating both dynamic and static embeddings into the event intensity function and optimizing the model via maximum likelihood estimation, DGNPP predicts events and occurrence time effectively. Experimental evaluations on three public datasets demonstrate that DGNPP achieves superior performance in event prediction and time prediction tasks with high efficiency, significantly outperforming baseline models and effectively mitigating the limitations of prior approaches.