k -means projective clustering
- 14 June 2004
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 155-165
- https://doi.org/10.1145/1055558.1055581
Abstract
In many applications it is desirable to cluster high dimensional data along various subspaces, which we refer to as projective clustering. We propose a new objective function for projective clustering, taking into account the inherent trade-off between the dimension of a subspace and the induced clustering error. We then present an extension of the k-means clustering algorithm for projective clustering in arbitrary subspaces, and also propose techniques to avoid local minima. Unlike previous algorithms, ours can choose the dimension of each cluster independently and automatically. Furthermore, experimental results show that our algorithm is significantly more accurate than the previous approaches.Keywords
This publication has 8 references indexed in Scilit:
- A Monte Carlo algorithm for fast projective clusteringPublished by Association for Computing Machinery (ACM) ,2002
- Finding generalized projected clusters in high dimensional spacesPublished by Association for Computing Machinery (ACM) ,2000
- Fast algorithms for projected clusteringPublished by Association for Computing Machinery (ACM) ,1999
- Centroidal Voronoi Tessellations: Applications and AlgorithmsSiam Review, 1999
- Automatic subspace clustering of high dimensional data for data mining applicationsPublished by Association for Computing Machinery (ACM) ,1998
- CUREPublished by Association for Computing Machinery (ACM) ,1998
- BIRCHPublished by Association for Computing Machinery (ACM) ,1996
- Extensions of Lipschitz mappings into a Hilbert spacePublished by American Mathematical Society (AMS) ,1984