Machine Learning

, Volume 87, Issue 1, pp 33–55

Visualizing non-metric similarities in multiple maps

Authors

    • Pattern Recognition and Bioinformatics LaboratoryDelft University of Technology
  • Geoffrey Hinton
    • Department of Computer ScienceUniversity of Toronto
Article

DOI: 10.1007/s10994-011-5273-4

Cite this article as:
van der Maaten, L. & Hinton, G. Mach Learn (2012) 87: 33. doi:10.1007/s10994-011-5273-4

Abstract

Techniques for multidimensional scaling visualize objects as points in a low-dimensional metric map. As a result, the visualizations are subject to the fundamental limitations of metric spaces. These limitations prevent multidimensional scaling from faithfully representing non-metric similarity data such as word associations or event co-occurrences. In particular, multidimensional scaling cannot faithfully represent intransitive pairwise similarities in a visualization, and it cannot faithfully visualize “central” objects. In this paper, we present an extension of a recently proposed multidimensional scaling technique called t-SNE. The extension aims to address the problems of traditional multidimensional scaling techniques when these techniques are used to visualize non-metric similarities. The new technique, called multiple maps t-SNE, alleviates these problems by constructing a collection of maps that reveal complementary structure in the similarity data. We apply multiple maps t-SNE to a large data set of word association data and to a data set of NIPS co-authorships, demonstrating its ability to successfully visualize non-metric similarities.

Keywords

Multidimensional scaling Embedding Data visualization Non-metric similarities

Copyright information

© The Author(s) 2011