GloDyNE: Global Topology Preserving Dynamic Network Embedding

Authors:
Publisher website
Google Scholar
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 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.
Funding Information
  • National Key Research and Development Program of China (2017YFB1003102)
  • Guangdong Provincial Key Laboratory (2020B121201001)
  • National Natural Science Foundation of China (61672478)
  • Program for Guangdong Introducing Innovative and Entrepreneurial Teams (2017ZT07X386)
  • Shenzhen Peacock Plan (KQTD2016112514355531)
  • National Leading Youth Talent Support Program of China