11th, 2009] Confirmed Invited Speakers: Prof.
Lenore Mullin (NSF Program
Director and SUNY Albany) and Prof.
James Raynolds (SUNY Albany). Talk
title: Tensors and n-d Arrays: Mathematics of Arrays, Psi-Calculus, and Composition
of Tensor and Array Operations.
[April 13th, 2009]
Confirmed Invited Speaker: Prof. Charles Elkan (University
of California, San Diego). Talk title:
Matrices with Missing Entries: Alternative Approaches.
[April 15th, 2009]
Confirmed Invited Speaker: Prof.
Leiven De Lathauwer (Katholieke
Universiteit Leuven, Belgium); Dr. **Lathauwer** is the
developer of HOSVD. Talk title: Tensor
Decompositions and Applications: a Survey.
20, 2009] Due to many requests, the deadline for paper submission has been
extended to May 5th, 2009.
The notification data has been
extended to May 25th, 2009.
1st, 2009] Workshop Proceedings is posted
16th, 2009] Workshop Program is posted
This workshop is a continuation of the theme of
SIGKDD 2008 Workshop on Data Mining using Matrices and Tensors (DMMT’08).
DMMT’08 is the first workshop on data mining using matrices and tensors held
annually with the SIGKDD Conference. Our 2008 workshop was indeed a success and
more than 100 people attend the workshop.
field of pattern recognition, data mining and machine learning increasingly
adapt methods and algorithms from advanced matrix computations, graph theory and
optimization. Prominent examples are spectral clustering, non-negative matrix
factorization, Principal component analysis (PCA) and Singular Value
Decomposition (SVD) related clustering and dimension reduction, tensor analysis, L-1 regularization, etc. Compared to
probabilistic and information theoretic approaches, matrix-based methods are
fast, easy to understand and implement; they are especially suitable for
parallel and distributed-memory computers to solve large scale challenging
problems such as searching and extracting patterns from the entire Web. Hence
the area of data mining using matrices and tensors is a popular and growing area
of research activities.
This workshop will
present recent advances in algorithms and methods using matrix and scientific
computing/applied mathematics for modeling and analyzing massive,
high-dimensional, and nonlinear-structured data. One main goal of the workshop
is to bring together leading researchers on many topic areas (e.g., computer
scientists, computational and applied mathematicians) to assess the
state-of-the-art, share ideas, and form collaborations. We also wish to attract
practitioners who seek novel ideas for applications. In summary, this workshop
will strive to emphasize the following aspects:
recent advances in algorithms and methods using matrix and scientific
- Addressing the
fundamental challenges in data mining using matrices and tensors
killer applications and key industry drivers (where theories and
interactions among researchers (from different backgrounds) sharing the same
interest to promote cross-fertilization of ideas.
benchmark data for better evaluation of the techniques
areas for the workshop include (but are not limited to) the following:
Methods and algorithms:
Component Analysis and Singular value decomposition for clustering and
matrix factorization for unsupervised and semi-supervised learning
- Spectral graph
Regularization and Sparsification
- Sparse PCA and
algorithms for matrix computation
- Web search and
Tensor analysis: Rank-1
Decomposition, PARAFAC/CANDECOMP, GLRAM/2DSVD,
decompositions (e.g., the Higher-Order SVD)
- Latent Semantic
Indexing and other developments for Information Retrieval
quadratic and semi-definite Programming
manifold learning and dimension reduction
statistics involving matrix computations
selection and extraction
learning (classification, semi-supervised learning and unsupervised
and extraction from Web
and information retrieval
computing and computational sciences
April 20, 2009 May 5th, 2009: Electronic submission of full papers
May 15th, 2009 May 25th, 2009: Author notification
May 20th, 2009 May 29th, 2009: Submission of Camera-ready papers
- June 28th, 2009: Workshop in
The electronic submission web site for research papers is available at:
Please register at Easychair first if you did not use EasyChair before.
Papers should be at most 10 pages long, single-spaced, in KDD conference
format, in font size 10 or larger with 1-inch margins on all sides.
|Program Committee Members
Tammy Kolda, Sandia National Labs
Jesse Barlow, Penn State University
Michael Berry, University of Tennessee
Yun Chi, NEC Laboratories America
Lars Elden, Linkping University, Sweden
Christos Faloutsos, Carnegie Mellon University
Estratis Gallopoulos, University of Patras
Joydeep Ghosh, University of Texas at Austin
Ming Gu, University of Califonia, Berkeley
Michael Jordan, University of California, Berkeley
Huan Liu, Arizona State University
Michael Ng, Hong Kong Baptist University
Haesun Park, Georgia Tech
Wei Peng, Xerox Research
Robert Plemmons, Wake Forest
Alex Pothen, Old Domino University
Yousef Saad, University of Minnesota
Horst Simon, Lawrence Berkeley National Laboratory
Gang Wang, Microsoft Research
Fei Wang, Florida International University
Kai Yu, NEC Laboratories America
Hongyuan Zha, Georgia Tech
Zhongyuan Zhang, Central University of Finance & Economics
Shenghuo Zhu, NEC Laboratories America