GloDyNE: Global Topology Preserving Dynamic Network Embedding

TL;DR

GloDyNE introduces a novel global topology-preserving dynamic network embedding method that efficiently updates node representations by diversely selecting representative nodes, outperforming existing methods in preserving overall network structure.

Contribution

It proposes a new node selection strategy combined with an incremental learning paradigm to better preserve global network topology in dynamic embeddings.

Findings

Achieves superior or comparable performance in downstream tasks.

Significantly outperforms others in graph reconstruction.

Effectively preserves global network topology.

Abstract

Learning low-dimensional topological representation of a network in dynamic environments is attracting much attention due to the time-evolving nature of many real-world networks. The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step. The idea of most existing DNE methods is to capture the topological changes at or around the most affected nodes (instead of all nodes) and accordingly update node embeddings. Unfortunately, this kind of approximation, although can improve efficiency, cannot effectively preserve the global topology of a dynamic network at each time step, due to not considering the inactive sub-networks that receive accumulated topological changes propagated via the high-order proximity. To tackle this challenge, we propose a novel node selecting strategy to diversely select the representative nodes over a network, which is coordinated with a new incremental learning paradigm of Skip-Gram based embedding approach. The extensive experiments show GloDyNE, with a small fraction of nodes being selected, can already achieve the superior or comparable performance w.r.t. the state-of-the-art DNE methods in three typical downstream tasks. Particularly, GloDyNE significantly outperforms other methods in the graph reconstruction task, which demonstrates its ability of global topology preservation. The source code is available at https://github.com/houchengbin/GloDyNE