Joint Learning of Evolving Links for Dynamic Network Embedding


  • Aakas Zhiyuli Renmin University of China
  • Xun Liang Renmin University of China
  • YanFang Chen Renmin University of China
  • Peng Shu Sogou, Inc., AD-Tech
  • Xiaoping Zhou Renmin University of China



node embedding, network embedding, dynamic networks


This paper studies the problem of learning node embeddings (a.k.a. distributed representations) for dynamic networks. The embedding methods allocate each node in network with a d-dimensions vector, which can generalize across various tasks, such as item recommendation, node labeling, and link prediction. In practice, many real-world networks are evolving with nodes/links added or deleted. However, most of the proposed methods are focusing on static networks. Although some previous researches have shown some promising results to handle the dynamic scenario, they just considered the added links and ignored the deleted ones. In this work, we designed a joint learning of added and deleted links model, named RDEM, for dynamic network embedding.




How to Cite

Zhiyuli, A., Liang, X., Chen, Y., Shu, P., & Zhou, X. (2018). Joint Learning of Evolving Links for Dynamic Network Embedding. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).