Jia-Yu Pan's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

AutoSplit: Fast and Scalable Discovery of Hidden Variables in Stream and Multimedia Databases

Jia-Yu Pan, Hiroyuki Kitagawa, Christos Faloutsos, and Masafumi Hamamoto. AutoSplit: Fast and Scalable Discovery of Hidden Variables in Stream and Multimedia Databases. In Proceedings of the The Eighth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2004), 2004.
Carlton Crest Hotel, Sydney, Australia, May 26~28, 2004 [Best Student Paper Award]

Download

[PDF]377.6kB  [gzipped postscript]441.9kB  

Abstract

For discovering hidden (latent) variables in real-world, non-gaussian data streams or an $n$-dimensional cloud of data points, SVD suffers from its orthogonality constraint. Our proposed method, ``AutoSplit'', finds features which are mutually independent and is able to discover non-orthogonal features. Thus, AutoSplit (a) finds more meaningful hidden variables and features, (b) it can easily lead to clustering and segmentation, (c) it surprisingly scales linearly with the database size and (d) it can also operate in on-line, single-pass mode. We also propose ``Clustering-AutoSplit'', which extends the feature discovery to multiple feature/bases sets, and leads to clean clustering.Experiments on multiple, real-world data sets show that our method meets all the properties above, outperforming the state-of-the-art SVD.

BibTeX Entry

@InProceedings{PAKDD04AutoSplit,
  author =	 {Jia-Yu Pan and Hiroyuki Kitagawa and Christos Faloutsos and Masafumi Hamamoto},
  title =	 {AutoSplit: Fast and Scalable Discovery of Hidden Variables in Stream and Multimedia Databases},
  booktitle =	 {Proceedings of the The Eighth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2004)},
  year =	 2004,
  wwwnote =	 {Carlton Crest Hotel, Sydney, Australia, May 26~28, 2004 <font color=red>[Best Student Paper Award]</font>},
  abstract =	 {For discovering hidden (latent) variables in real-world, non-gaussian data streams or an $n$-dimensional cloud of data points, SVD suffers from its orthogonality constraint. Our proposed method, ``AutoSplit'', finds features which are mutually independent and is able to discover non-orthogonal features. Thus, AutoSplit (a) finds more meaningful hidden variables and features, (b) it can easily lead to clustering and segmentation, (c) it surprisingly scales linearly with the database size and (d) it can also operate in on-line, single-pass mode. We also propose ``Clustering-AutoSplit'', which extends the feature discovery to multiple feature/bases sets, and leads to clean clustering.
Experiments on multiple, real-world data sets show that our method meets all the properties above, outperforming the state-of-the-art SVD.
},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Multimedia Data Mining},
}

Generated by bib2html (written by Patrick Riley ) on Wed Sep 01, 2004 13:24:30