HONEM: Learning Embedding for Higher Order Networks.

Journal: Big data
Published Date: Aug 1, 2020

Abstract

Representation learning on networks offers a powerful alternative to the oft painstaking process of manual feature engineering, and, as a result, has enjoyed considerable success in recent years. However, all the existing representation learning methods are based on the first-order network, that is, the network that only captures the pairwise interactions between the nodes. As a result, these methods may fail to incorporate non-Markovian higher order dependencies in the network. Thus, the embeddings that are generated may not accurately represent the underlying phenomena in a network, resulting in inferior performance in different inductive or transductive learning tasks. To address this challenge, this study presents higher order network embedding (HONEM), a higher order network (HON) embedding method that captures the non-Markovian higher order dependencies in a network. HONEM is specifically designed for the HON structure and outperforms other state-of-the-art methods in node classification, network reconstruction, link prediction, and visualization for networks that contain non-Markovian higher order dependencies.

Authors

  • Mandana Saebi
    Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA.
  • Giovanni Luca Ciampaglia
    Department of Computer Science and Engineering, University of South Florida, Tampa, Florida, USA.
  • Lance M Kaplan
    U.S. Army Research Laboratory, Adelphi, Maryland, USA.
  • Nitesh V Chawla
    Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556, USA.; Interdisciplinary Center for Network Science and Applications, University of Notre Dame, Notre Dame, IN 46556, USA.Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN 46556, USA.Environmental Change Initiative, University of Notre Dame, Notre Dame, IN 46556, USA.; Interdisciplinary Center for Network Science and Applications, University of Notre Dame, Notre Dame, IN 46556, USA.Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN 46556, USA.Environmental Change Initiative, University of Notre Dame, Notre Dame, IN 46556, USA.

Keywords

External Resources

Popular Topics
Recent Journals