DM: Second Call for Papers on the special issue on Instance

[owner-datamine-l]

Selection
Date: Tue, 01 Jun 1999 11:29:59 +0900
From: motoda@ar.sanken.osaka-u.ac.jp (Hiroshi Motoda)
Sender: owner-datamine-l@nautilus-sys.com
Precedence: bulk

[Sorry if you receive this multiple times.]

------------------------------------------------------------------

Call for Papers - INSTANCE SELECTION 

A Special Issue of the Data Mining and Knowledge Discovery Journal

http://www.comp.nus.edu.sg/~liuh/dmkd.html
Due date: 18 Sept 1999, electronic submission

INTRODUCTION 

Knowledge discovery and data mining (KDD) is growing rapidly as
computer technologies advance.  However, no matter how powerful
computers are now or will be in the future, KDD researchers and
practitioners must consider how to manage ever-growing data
which is, ironically, due to the extensive use of computers and
ease of data collection with computers.  Many different
approaches have been used to address the data explosion
issue. Algorithm scale-up is one and data reduction is
another. Instance, example, or tuple selection is about
algorithms that select or search for a representative portion of
data that can fulfill a KDD task as if the whole data is used.
Instance selection is directly related to data reduction and
becomes increasingly important in many KDD applications due to
the need for processing efficiency and/or storage
efficiency. One of the major means of instance selection is
sampling whereby a sample is selected for testing and analysis,
and randomness is a key element in the process. Instance
selection also covers other methods that require search.
Examples can be found in density estimation - finding the
representative instances (data points) for each cluster, and
boundary hunting - finding the critical instances to form
boundaries to differentiate data points of different
classes. Other important issues related to instance selection
extend to unwanted precision, focusing, concept drifts,
noise/outlier removal, data smoothing, etc.

OBJECTIVES

This special issue on instance selection brings researchers and
practitioners together to report new developments and
applications, share hard-learned experiences to avoid similar
pitfalls, and shed light on the future development of instance
selection. Several critical questions are interesting to
practitioners in KDD, and practically useful in real-life
applications:

* What are the existing methods? 
* Are they the same or just different names coined by
  researchers in different fields? 
* Are they application dependent or stand-alone?
* Are new methods needed?
* If there is no generic selection algorithm, are these
  algorithms specific to tasks such as classification,
  clustering, association, parallelization?
* Are there common and reusable components in instance selection
  methods?
* How can we reconfigure some components of instance selection
  for a particular task/application?
* What are the new challenging issues of instance selection in
  the context of KDD? 

Sensible answers to these questions can greatly advance the
field of KDD in handling large databases. This special issue
hopes to answer these questions and to provide an easy reference
point for further research and development.

COVERAGE 

All aspects of instance selection will be considered: theories,
methodologies, algorithms, and applications. Also studied are
issues such as costs of selection, the gains and losses due to
the selection, how to balance the gains and losses, and when to
use what.

Researchers and practitioners in KDD-related fields (Statistics,
Databases, Machine Learning, etc.) are encouraged to submit
their work to this special issue to share and exchange ideas and
problems in any forms: survey, research manuscript, experimental
comparison, theoretical study, or report on applications.

IMPORTANT DATES

18 September, 1999  - Submissions due 

15 November, 1999   - Reviews due (mainly peer review and the
                      guest editors will review all the
                      submissions)

22 Janurary, 2000   - Revised papers due 

13 February, 2000   - To Editor-in-Chief 


FORMAT and PAGE LIMIT

Each submission should be no more than 25 pages, have a line
spacing of 1.5, use no smaller than a 12pt font, and have at
least a 1 inch margin on each side.

CONTACT INFORMATION

Please direct any enquiries to the guest editors: 

Huan Liu, liuh@comp.nus.edu.sg, National University of Singapore

Hiroshi Motoda, motoda@sanken.osaka-u.ac.jp, Osaka University, Japan.

Please submit your work electronically (postscript file) to
either guest editor. If you have to submit it in hard copy,
please discuss it with the guest editors first.

INFORMATION about the JOURNAL

Data Mining and Knowledge Discovery</a>, Kluwer Academic
Publishers.  http://www.wkap.nl/journalhome.htm/1384-5810
Editors-in-Chief: Usama Fayyad, Gregory Piatetsky-Shapiro,
Heikki Mannila.