Information Bottleneck for Non Co-Occurrence Data

@inproceedings{6576,
  title = {Information Bottleneck for Non Co-Occurrence Data},
  journal = {In Advances in Neural Information Processing Systems 19, 2007 (NIPS 2006)},
  booktitle = {Advances in Neural Information Processing Systems 19},
  abstract = {We present a general model-independent approach to the analysis of data in cases when these data do not appear in the form of co-occurrence of two variables X, Y, but rather as a sample of values of an unknown (stochastic) function Z(X,Y). For example, in gene expression data, the expression level Z is a function of gene X and condition Y; or in movie ratings data the rating Z is a function of viewer X and movie Y . The approach represents a consistent extension of the Information Bottleneck method that has previously relied on the availability of co-occurrence statistics. By altering the relevance variable we eliminate the need in the sample of joint distribution of all input variables. This new formulation also enables simple MDL-like model complexity control and prediction of missing values of Z. The approach is analyzed and shown to be on a par with the best known clustering algorithms for a wide range of domains. For the prediction of missing values (collaborative filtering) it improves the currently best known results.},
  pages = {1241-1248},
  editors = {Sch{\"o}lkopf, B. , J. Platt, T. Hofmann},
  publisher = {MIT Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, MA, USA},
  month = sep,
  year = {2007},
  author = {Seldin, Y. and Slonim, N. and Tishby, N.},
  month_numeric = {9}
}