Graph Neural Point Process for Temporal Interaction Prediction

Temporal graphs are ubiquitous data structures in many scenarios, including social networks, user-item interaction networks, etc. In this paper, we focus on predicting the exact time of future interactions between node pairs on a temporal graph. This problem can support interesting applications including time-sensitive items recommendation, congestion prediction on road networks, etc. We present the Graph Neural Point Process (GNPP) to tackle this problem. GNPP relies on the graph neural message passing and the temporal point process framework. Most previous graph neural models devised for temporal graphs either utilize the chronological order information or rely on specific point process models, ignoring the exact timestamps and complicated temporal patterns. In GNPP, we adapt a time encoding scheme to map real-valued timestamps to a high-dimensional vector space so that the temporal information can be modeled precisely. Further, GNPP considers the structural information of graphs by conducting message passing aggregation on the constructed line graph. The obtained representation defines a neural conditional intensity function that models events’ generation mechanisms for predicting interactions’ time between node pairs. We evaluate this model on several synthetic and real-world temporal graphs where it outperforms recently proposed neural point process models and graph neural models devised for temporal graphs. We further conduct ablation comparisons and visual analyses to shed some light on the learned model and understand the functionality of important components comprehensively.

1 Introduction

Graphs are ubiquitous data structures in modern applications, ranging from social networks, financial transactions and e-commerce platforms. For many practical scenarios, these graphs are often combined with temporal information, indicating dynamic characteristics, i.e., temporal graphs. For example, financial transactions have occurring timestamps; users’ browsing records for products on e-commerce platforms are associated with timestamps as well. The dynamic patterns on graphs are of both research and practical interest, e.g., counting pattern’s occurrences and predicting future interactions [1], [2].