Name
Abstract | ||
|---|---|---|
Due to the vast amount and pace of high-dimensional data production and their distribution among network nodes, the fields of Distributed Knowledge Discovery (DKD) and Distributed Dimensionality Reduction (DDR) have emerged as a necessity in many application areas. While a wealth of centralized dimensionality reduction (DR) algorithms is available, only few have been proposed for distributed environments, most of them adaptations of centralized ones. In this paper, we introduce K-Landmarks, a new DDR algorithm, and we evaluate its comparative performance against a set of well known distributed and centralized DR algorithms. We primarily focus on each algorithm's performance in maintaining clustering quality throughout the projection, while retaining low stress values. Our algorithm outperforms most other algorithms, showing its suitability for highly distributed environments. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11871637_32 | PKDD |
Keywords | Field | DocType |
knowledge discovery,dimensionality reduction,centralized dimensionality reduction,clustering quality maintenance,new ddr algorithm,low stress value,centralized dr algorithm,high-dimensional data production,application area,comparative performance,clustering quality,dimension reduction,distributed environment,high dimensional data | Distributed knowledge,Data mining,Pace,Dimensionality reduction,Computer science,Node (networking),Distributed algorithm,Knowledge extraction,Online analytical processing,Cluster analysis,Distributed computing | Conference |
Volume | ISSN | ISBN |
4213 | 0302-9743 | 3-540-45374-1 |
Citations | PageRank | References |
5 | 0.51 | 7 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Panagis Magdalinos | 1 | 35 | 5.55 |
| Christos Doulkeridis | 2 | 899 | 55.91 |
| Michalis Vazirgiannis | 3 | 3942 | 268.00 |