Call for papers

The Workshop on new challenges for feature selection in data mining and knowledge discovery (FSDM2008) serves as a forum for researchers in the fields of statistics, pattern recognition, machine learning, and data mining to exchange ideas and present recent work. The official language of the conference is English. FSDM 2008 will be organised jointly by Ghent University, The University of the Basque Country, the University of Liège and Arizona State University, in collaboration with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2008).

The workshop invites papers relevant to research in feature selection in the broad sense, and especially welcomes contributions that highlight emerging feature selection challenges associated with new mining tasks. Possible paper topics include, but are not limited to:

  • Dimensionality reduction
  • Feature weighting
  • Feature ranking
  • Subset selection
  • Feature extraction/construction
  • Feature selection methodology
  • Integration with data mining algorithms
  • Ensemble methods
  • Pitfalls and learned lessons in feature selection studies
  • Real-world case studies and applications that highlight the role of feature selection
  • Cross-discipline comparative studies (different types of bio-data, text, Web, ...)
  • Novel data structures
  • Selection in small sample domains
  • Data streams and time series
  • Feature selection for labeled and unlabeled data
  • Modeling variable and feature selection
  • Feature selection bias and variance
  • Selection in extremely high-dimensional domains
  • Novel univariate and multivariate metrics for feature selection

Paper submission guidelines

The papers must be in English and must be formatted according to the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines. Authors instructions and style files can be downloaded at http://www.springer.de/comp/lncs/authors.html. We recommend a maximum length of at most 12 pages in this format (a solid motiviation is needed for exceeding this limit), including figures, title pages, references, and appendices.

We also welcome (shorter) papers presenting new ideas or thought-provoking issues.

Accepted papers of FSDM'08 will be published in the JMLR (Journal of Machine Learning Research) Workshop and Conference Proceedings series.

Paper submission website

Papers should be submitted as PDF files using the submission site

http://www.easychair.org/conferences/?conf=fsdm08