Workshop on Research Issues in Data Mining and Knowledge Discovery DMKD 2001

http://www.cs.cornell.edu/johannes/dmkd2001.htm 
Santa Barbara, CA -- May 20th, 2001
In conjunction with the ACM SIGMOD/PODS 2001 Conference
Funding for this workshop has been provided by IBM Research.

PRELIMINARY WORKSHOP PROGRAM

(Online version of the papers can be found at the end of this page.)

9:00 DMKD Opening and Invited Talk: “Crossing the Analytical-Chasm:  Applying Data Mining Successfully.” Brian Lent, President and CEO, Intelligent Results, Inc.

10:00-10:50 First paper session

• Padhraic Smyth. Breaking Out of the Black-Box: Research Challenges in Data Mining.
• Jian Pei, Anthony K.H. Tung, and Jiawei Han. Fault-Tolerant Frequent Pattern Mining:  Problems and Challenges.

10:50-11:00 Short Coffee Break

11:00-12:40 Second paper session

• Baohua Gu, Bing Liu, Feifant Hu, and Huan Liu. Efficiently Determine the Starting Sample Size for Progressive Sampling.
• Xiong Wang. Mining Protein Surfaces.
• George Kollios, Stan Sclaroff and Margrit Betke. Motion Mining:  Discovering Spatio-Temporal Patterns in Databases of Human Motion.
• Qin Ding, William Perizo, Qiang Ding, and Amalendu Roy. On Mining Satellite and Other Remotely Sensed Images.

12:40-2:00 Lunch break

2:00-3:00 Invited talk: Title "An Industry Perspective on DMKD Research Issues".
Ramasamy Uthurusamy, General Motors.

3:00-3:30 Coffee break

3:30-4:45 Third paper session

• Minos Garofalakis and Rajeev Rastogi. Data Mining Meets Network Management:  The NEMESIS Project.
• Pedro Domingos and Geoff Hulten. Catching Up with the Data:  Research Issues in Mining Data Streams.
• Jochen Hipp, Ulrich Guntzer, and Udo Grimmer. Data Quality Mining - Making a Virtue of Necessity.

4:45 Closing remarks and end of workshop

WORKSHOP OBJECTIVES

The Workshop on Research Issues in Data Mining and Knowledge Discovery (DMKD) was started five years ago to foster discussion and investigation of data mining research issues pertinent to large databases and data warehouses. Over these years, data mining as a discipline has matured considerably. Particularly strong progress has been made in the design of scalable algorithms that transform the oceans of bits in very large databases into interpretable patterns and predictive models.

This year's sixth DMKD workshop is aimed at discussing the next generation of data mining research, with the goal of bringing together researchers and experienced practitioners from academia and industry. The atmosphere of the workshop will be informal, fostering interaction through short presentations and open discussion of new research visions and industrial experiences. The workshop is being held in cooperation with SIGMOD/PODS 2001.

TOPICS OF INTEREST

• New applications of data mining
• Industrial experiences with data mining projects
• Limitation of the current generation of data mining tools
• Intersection of data mining with other disciplines
• Research visions: Where is data mining in 2010?

SUBMISSION GUIDELINES

Papers should be no more than six pages. The workshop accepts only electronic submission of papers in ASCII, HTML, PDF, or PostScript format to either of the two workshop chairs (bayardo@almaden.ibm.com or johannes@cs.cornell.edu). Accepted papers will be included in the informal proceedings made available to the workshop attendees and online.

IMPORTANT DATES

• Submission deadline: April 2, 2001
• Notification: April 23, 2001
• Camera-ready due: May 7, 2001
• Workshop: May 20, 2001

REGISTRATION

There is no separate registration fee for the workshop; registration is included in the SIGMOD/PODS 2001 registration.

STUDENT TRAVEL SCHOLARSHIPS

Limited amount of funding is available for travel expenses for student participants in the workshop. Priority will be given to students who are (co-)authors of accepted papers in the workshop. To apply for student scholarships, send email to Roberto Bayardo or Johannes Gehrke by April 30.

WORKSHOP CHAIRS

• Roberto Bayardo (IBM Almaden Research Lab, bayardo@almaden.ibm.com)
• Johannes Gehrke (Cornell University, johannes@cs.cornell.edu)

PROGRAM COMMITTEE

• Paul Bradley, digiMine Inc.
• Charu C. Aggarwal, IBM T. J. Watson Research Center.
• Dimitrios Gunopulos, UCR.
• Martin Ester, University of Munich.
• Venkatesh Ganti, Microsoft Research.
• Minos Garofalakis, Bell Laboratories.
• Jiawei Han, Simon Fraser University.
• Bing Liu, National University of Singapore.
• Heikki Mannila. Nokia Research Center.
• Flip Korn, AT&T Labs -- Research.
• Vipin Kumar. University of Minnesota.
• Sharad Mehrotra, University of California.
• Sridhar Ramaswamy, Epiphany.
• Kyuseok Shim, KAIST.
• Mohammed J. Zaki, Rensselaer Polytechnic Institute.

ACCEPTED PAPERS ONLINE:

FULL PAPERS:

• Minos Garofalakis and Rajeev Rastogi. Data Mining Meets Network Management:  The NEMESIS Project.
• Padhraic Smyth. Breaking Out of the Black-Box: Research Challenges in Data Mining
• Jian Pei, Anthony K.H. Tung, and Jiawei Han. Fault-Tolerant Frequent Pattern Mining:  Problems and Challenges.
• Baohua Gu, Bing Liu, Feifant Hu, and Huan Liu. Efficiently Determine the Starting Sample Size for Progressive Sampling.
• Jochen Hipp, Ulrich Guntzer, and Udo Grimmer. Data Quality Mining - Making a Virtue of Necessity.
• David Skalak. Speed-up Mining or "Why is data mining iterative?"
• Qin Ding, William Perizo, Qiang Ding, and Amalendu Roy. On Mining Satellite and Other Remotely Sensed Images.
• Pedro Domingos and Geoff Hulten. Catching Up with the Data:  Research Issues in Mining Data Streams.
• George Kollios, Stan Sclaroff and Margrit Betke. Motion Mining:  Discovering Spatio-Temporal Patterns in Databases of Human Motion.
• Xiong Wang. Mining Protein Surfaces.

POSITION PAPERS:

• Jose Maria Peña and Ernestina Menasalvas. Towards Flexibility in a Distributed Data Mining Framework.
• Mihael Ankerst. Human Involvement and Interactivity of the Next Generation's Data Mining Tools.