Data Mining and Knowledge Discovery: A Special Issue on

Data Mining with Matrices, Graphs and Tensors (Call for Paper)

Guest Editors

Tao Li, Chris Ding and Fei Wang

The field of data mining increasingly adapts 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, and L-1 regularization. Compared to probabilistic and information theoretic approaches, matrix-based methods are fast, easy to understand and implement, and they are especially suited for parallel and distributed-memory computers to solve large-scale challenges such as searching and extracting patterns from the entire Web. Hence, the area of data mining using matrices, graphs and tensors is a popular and growing area of research activities.

This special issue will provide a leading forum for timely, in-depth presentation of recent advances in algorithms, theory and applications in the field of data mining with matrices, graphs and tensors.

Topics of Interest

The major topics of the special issue include but certainly are not limited to:

• Principal component analysis and singular value decomposition for clustering and dimension reduction
• Nonnegative matrix factorization for unsupervised and semi-supervised learning
• Spectral graph clustering
• L-1 regularization and sparsification
• Sparse PCA and SVD
• Randomized algorithms for matrix computation
• Web search and ranking algorithms
• Canonical decompositions (CANDECOMP/PARAFAC)
• Tensor analysis: Rank-1 decomposition, PARAFAC/CANDECOMP, GLRAM/2DSVD, Tucker decompositions (e.g., the Higher-Order SVD)
• GSVD for classification
• Latent semantic indexing and other developments for information retrieval
• Linear, quadratic and semi-definite programming
• Non-linear manifold learning and dimension reduction
• Computational statistics involving matrix computations
• Feature selection and extraction
• Graph-based learning (classification, semi-supervised learning and unsupervised learning)
• Case Studies and Applications
  • Information search and extraction from the Web
  • Text processing and information retrieval
  • Image processing and analysis
  • Genomics and bioinformatics
  • Scientific computing and computational sciences
  • Social networks

Submission Guidelines

Manuscripts should be submitted to http://DAMI.edmgr.com. Authors should choose Article Type Data Mining with Matrices when submitting to this special issue.

Important Dates

Full Paper Submission:     May 1, 2009

Author Notification:       Nov 1, 2009

Paper Revision Due:       Nov 22, 2009

Special Issue Guest Editors

Tao Li, Florida International University, taoli@cs.fiu.edu

Chris Ding, University of Texas at Arlington, CHQDing@uta.edu

Fei Wang, Florida International University, feiwang@cs.fiu.edu

Related Links

KDD 2009 Workshop on Data Mining using Matrices and Tensors

KDD 2008 Workshop on Data Mining using Matrices and Tensors

CIKM 2008 Tutorial on Information and Knowledge Management Using Matrices and Graphs

SDM 2009 Tutorial on Data Mining with Graphs and Matrices