EPNE: Evolutionary Pattern Preserving Network Embedding

TL;DR

EPNE introduces a novel temporal network embedding approach that captures evolutionary patterns of nodes over time, enhancing prediction accuracy by integrating temporal and structural information.

Contribution

The paper presents EPNE, a new model that preserves evolutionary patterns in dynamic networks using time-frequency domain analysis and a combined temporal-structural objective.

Findings

EPNE outperforms existing methods in prediction tasks.

Model effectively captures both periodic and non-periodic evolutionary patterns.

Temporal information significantly improves embedding quality.

Abstract

Information networks are ubiquitous and are ideal for modeling relational data. Networks being sparse and irregular, network embedding algorithms have caught the attention of many researchers, who came up with numerous embeddings algorithms in static networks. Yet in real life, networks constantly evolve over time. Hence, evolutionary patterns, namely how nodes develop itself over time, would serve as a powerful complement to static structures in embedding networks, on which relatively few works focus. In this paper, we propose EPNE, a temporal network embedding model preserving evolutionary patterns of the local structure of nodes. In particular, we analyze evolutionary patterns with and without periodicity and design strategies correspondingly to model such patterns in time-frequency domains based on causal convolutions. In addition, we propose a temporal objective function which is optimized simultaneously with proximity ones such that both temporal and structural information are preserved. With the adequate modeling of temporal information, our model is able to outperform other competitive methods in various prediction tasks.