Similarity Estimation using Bayes Ensembles

Published at 22nd International Conference on Scientific and Statistical Database Management (SSDBM)

Conference Date: June 30^th to July 2^nd of 2010
Conference Location: Heidelberg, Germany
Conference Title: 22^nd International Conference on Scientific and Statistical Database Management (SSDBM), Heidelberg, Germany, 2010
Conference Chairs: Andreas Reuter, Michael Gertz Conference Co-Chairs: Tony Hey, Bertram Ludäscher

Abstract

Similarity search and data mining often rely on distance or similarity functions in order to provide meaningful results and semantically meaningful patterns. However, standard distance measures like L_p-norms are often not capable to accurately mirror the expected similarity between two objects. To bridge the so-called semantic gap between feature representation and object similarity, the distance function has to be adjusted to the current application context or user. In this paper, we propose a new probabilistic framework for estimating a similarity value based on a Bayesian setting. In our framework, distance comparisons are modeled based on distribution functions on the difference vectors. To combine these functions, a similarity score is computed by an Ensemble of weak Bayesian learners for each dimension in the feature space. To find independent dimensions of maximum meaning, we apply a space transformation based on eigenvalue decomposition. In our experiments, we demonstrate that our new method shows promising results compared to related Mahalanobis learners on several test data sets w.r.t. nearest-neighbor classification and precision-recall-graphs.

Copyright Notes

Tobias Emrich, Franz Graf, Hans-Peter Kriegel, Matthias Schubert, Marisa Thoma
"Similarity Estimation using Bayes Ensembles", 22nd International Conference on Scientific and Statistical Database Management (SSDBM), Heidelberg, Germany, 2010.

M. Gertz and B. Ludäscher (Eds.): SSDBM 2010, LNCS 6187, pp. 537–554, 2010.
© Springer-Verlag Berlin Heidelberg 2010

DOI: 10.1007/978-3-642-13818-8_37

Documents

This is the author’s version of the work. It is posted here by permission of Springer for your personal use. Not for redistribution.

Paper
Poster
Talk

BibTex

@INPROCEEDINGS{EmrGraKriSchetal10a,
  AUTHOR    = {Emrich, Tobias and Graf, Franz and Kriegel, Hans-Peter
              and Schubert, Matthias and Thoma, Marisa},
  TITLE     = {Similarity Estimation using Bayes Ensembles},
  BOOKTITLE = {Proceedings of the 22nd International Conference on
              Scientific and Statistical Database Management (SSDBM),
              Heidelberg, Germany},
  VOLUME    = {6187},
  PAGES     = {537–-554},
  YEAR      = {2010},
  DOI       = {10.1007/978-3-642-13818-8_37}
}