GloDyNE: Global Topology Preserving Dynamic Network Embedding

by   Chengbin Hou, et al.

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


page 1

page 2

page 3

page 4


DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

Learning topological representation of a network in dynamic environments...

Robust Dynamic Network Embedding via Ensembles

Dynamic Network Embedding (DNE) has recently attracted considerable atte...

Time-varying Graph Representation Learning via Higher-Order Skip-Gram with Negative Sampling

Representation learning models for graphs are a successful family of tec...

Decoupled Variational Embedding for Signed Directed Networks

Node representation learning for signed directed networks has received c...

Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling

Network representation learning, as an approach to learn low dimensional...

GoT-WAVE: Temporal network alignment using graphlet-orbit transitions

Global pairwise network alignment (GPNA) aims to find a one-to-one node ...

Learning Dynamic Preference Structure Embedding From Temporal Networks

The dynamics of temporal networks lie in the continuous interactions bet...

Please sign up or login with your details

Forgot password? Click here to reset