articleNov 6, 2017Closed access

HIN2Vec

Pennsylvania State University

Indexed incrossref

Abstract

In this paper, we propose a novel representation learning framework, namely HIN2Vec, for heterogeneous information networks (HINs). The core of the proposed framework is a neural network model, also called HIN2Vec, designed to capture the rich semantics embedded in HINs by exploiting different types of relationships among nodes. Given a set of relationships specified in forms of meta-paths in an HIN, HIN2Vec carries out multiple prediction training tasks jointly based on a target set of relationships to learn latent vectors of nodes and meta-paths in the HIN. In addition to model design, several issues unique to HIN2Vec, including regularization of meta-path vectors, node type selection in negative sampling,…

Citation impact

618
total citations
FWCI
46.19
Percentile
100%
References
27
Citations per year

Authors

3

Topics & keywords

Keywords
  • Computer science
  • Node (physics)
  • Semantics (computer science)
  • Artificial intelligence
  • Feature learning
  • Representation (politics)
  • Regularization (linguistics)
  • Set (abstract data type)
No related works found for this paper.

Funding