DHPrep: Deep Hawkes Process based Dynamic Network Representation

TL;DR

DHPrep introduces a deep learning approach using Hawkes processes to effectively capture and model the temporal dynamics of evolving networks, improving tasks like link prediction and vertex recommendation.

Contribution

This paper presents DHPrep, a novel deep Hawkes process-based algorithm that models temporal dynamics in dynamic network representations, integrating structural and temporal information.

Findings

DHPrep outperforms state-of-the-art methods in link prediction.

DHPrep effectively captures temporal evolution of network structures.

Experimental results validate the superiority of DHPrep on real-world datasets.

Abstract

Networks representation aims to encode vertices into a low-dimensional space, while preserving the original network structures and properties. Most existing methods focus on static network structure without considering temporal dynamics. However, in real world, most networks (e.g., social and biological networks) are dynamic in nature and are constantly evolving over time. Such temporal dynamics are critical in representations learning, especially for predicting dynamic networks behaviors. To this end, a Deep Hawkes Process based Dynamic Networks Representation algorithm (DHPrep) is proposed in this paper, which is capable of capturing temporal dynamics of dynamic networks. Specifically, DHPrep incorporates both structural information and temporal dynamics to learn vertices representations that can model the edge formation process for a vertex pair, where the structural information is used to capture the historical impact from their neighborhood, and the temporal dynamics utilize this historical information and apply Hawkes point process to model the edges formation process. Moreover, a temporal smoother is further imposed to ensure the representations evolve smoothly over time. To evaluate the effectiveness of DHPrep, extensive experiments are carried out using four real-world datasets. Experimental results reveal that our DHPrep algorithm outperforms state-of-the-art baseline methods in various tasks including link prediction and vertices recommendation.