Convex Co-embedding

Authors

  • Farzaneh Mirzazadeh University of Alberta
  • Yuhong Guo Temple University
  • Dale Schuurmans University of Alberta

DOI:

https://doi.org/10.1609/aaai.v28i1.8976

Keywords:

Convex, Co-embedding

Abstract

We present a general framework for association learning, where entities are embedded in a common latent space to express relatedness by geometry -- an approach that underlies the state of the art for link prediction, relation learning, multi-label tagging, relevance retrieval and ranking. Although current approaches rely on local training applied to non-convex formulations, we demonstrate how general convex formulations can be achieved for entity embedding, both for standard multi-linear and prototype-distance models. We investigate an efficient optimization strategy that allows scaling. An experimental evaluation reveals the advantages of global training in different case studies.

Downloads

Published

2014-06-21

How to Cite

Mirzazadeh, F., Guo, Y., & Schuurmans, D. (2014). Convex Co-embedding. Proceedings of the AAAI Conference on Artificial Intelligence, 28(1). https://doi.org/10.1609/aaai.v28i1.8976

Issue

Section

Main Track: Novel Machine Learning Algorithms