Definition
From database perspective, dimensionality reduction (DR) is to map the original high-dimensional data into a lower-dimensional representation that captures the content in the original data, according to some criterion. Formally, given a data point P = {p1, p2,…,pD} in D-dimensional space, DR is to find a d-dimensional subspace, where d < D, such that P is represented by a d-dimensional point by projecting P into the d-dimensional subspace.
Key Points
Advances in data collection and storage capabilities have led to an information overload in most sciences. Many new and emerging data types, such as multimedia, time series, and biological sequence, have been studied extensively in the past and present new challenges in data analysis and management due to their high dimensionality of data space. One known phenomenon of “dimensionality curse” leads traditional data access methods to fail. High-dimensional datasets present many mathematical challenges as well as some...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. Science. 2000;290(5500):2323–6.
Shen HT, Zhou X, Zhou A. An adaptive and dynamic dimensionality reduction method for high-dimensional indexing. VLDB J. 2007;16(2):219–34.
Zhu X, Huang Z, Shen HT, Cheng J, Xu C. Dimensionality reduction by mixed kernel canonical correlation analysis. Pattern Recogn. 2012;45(8):3003–16.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2018 Springer Science+Business Media, LLC, part of Springer Nature
About this entry
Cite this entry
Shen, H.T. (2018). Dimensionality Reduction. In: Liu, L., Özsu, M.T. (eds) Encyclopedia of Database Systems. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-8265-9_551
Download citation
DOI: https://doi.org/10.1007/978-1-4614-8265-9_551
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-8266-6
Online ISBN: 978-1-4614-8265-9
eBook Packages: Computer ScienceReference Module Computer Science and Engineering