Clustering on the Unit Hypersphere using von Mises-Fisher Distributions

  title={Clustering on the Unit Hypersphere using von Mises-Fisher Distributions},
  author={Arindam Banerjee and Inderjit S. Dhillon and Joydeep Ghosh and Suvrit Sra},
  journal={Journal of Machine Learning Research},
Several large scale data mining applications, such as text c ategorization and gene expression analysis, involve high-dimensional data that is also inherentl y directional in nature. Often such data is L2 normalized so that it lies on the surface of a unit hyperspher e. Popular models such as (mixtures of) multi-variate Gaussians are inadequate for characteri zing such data. This paper proposes a generative mixture-model approach to clustering directional data based on the von Mises-Fisher (vMF… CONTINUE READING
Highly Influential
This paper has highly influenced 72 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 617 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 351 extracted citations

Machine Learning and Medical Imaging

View 4 Excerpts
Highly Influenced

movMF : An R Package for Fitting Mixtures of von Mises-Fisher Distributions

WU Wirtschaftsuniversität Wien, Johannes Kepler
View 12 Excerpts
Highly Influenced

Spherical Paragraph Model

View 4 Excerpts
Highly Influenced

App Miscategorization Detection: A Case Study on Google Play

IEEE Transactions on Knowledge and Data Engineering • 2017
View 4 Excerpts
Highly Influenced

617 Citations

Citations per Year
Semantic Scholar estimates that this publication has 617 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-3 of 3 references

distributions”, pages 365–385

K. V. Mardia, P. Jupp
View 4 Excerpts
Highly Influenced

A comparison of document cluste

Press, 1997. M. Steinbach, G. Karypis, V. Kumar

Similar Papers

Loading similar papers…