Spread-gram: A spreading-Activation schema of network structural learning

Jie Bai, Linjing Li, Daniel Zeng

Research output: Contribution to journalArticlepeer-review

Abstract

Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this scheme, we learn node embeddings by adjusting the proximity of nodes traversing the spreading structure of the network. Our proposed method shows a significant improvement in multiple analysis tasks based on various real-world networks, ranging from semantic networks to protein interaction networks, international trade networks, human behavior networks, etc. In particular, our model can effectively discover the hierarchical structures in networks. The well-organized model training speeds up the convergence to only a small number of iterations, and the training time is linear with respect to the edge numbers.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Sep 30 2019
Externally publishedYes

Keywords

  • Cognitive psychology
  • Network analysis
  • Node embeddings
  • Representation learning
  • Spreading Activation

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Spread-gram: A spreading-Activation schema of network structural learning'. Together they form a unique fingerprint.

Cite this