Randomized approaches for nearest neighbor search in metric space when computing the pairwise distance is extremely expensive

Authors:
Lusheng Wang;Yong Yang;Guohui Lin
Affiliations:
Department of Computer Science, City University of Hong Kong, Hong Kong;Department of Computer Science, City University of Hong Kong, Hong Kong;Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada
Venue:
AAIM'10 Proceedings of the 6th international conference on Algorithmic aspects in information and management
Year:
2010

Citing 10
Cited 0

An algorithm for finding nearest neighbours in (approximately) constant average time

Pattern Recognition Letters
A new version of the nearest-neighbour approximating and eliminating search algorithm (AESA) with linear preprocessing time and memory requirements

Pattern Recognition Letters
The choice of reference points in best-match file searching

Communications of the ACM
On the closest string and substring problems

Journal of the ACM (JACM)
Similarity Search without Tears: The OMNI Family of All-purpose Access Methods

Proceedings of the 17th International Conference on Data Engineering
M-tree: An Efficient Access Method for Similarity Search in Metric Spaces

VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
Searching in metric spaces by spatial approximation

The VLDB Journal — The International Journal on Very Large Data Bases
Comparison of AESA and LAESA search algorithms using string and tree-edit-distances

Pattern Recognition Letters
Pivot selection techniques for proximity searching in metric spaces

Pattern Recognition Letters
Similarity Search: The Metric Space Approach (Advances in Database Systems)

Similarity Search: The Metric Space Approach (Advances in Database Systems)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Finding the closest object for a query in a database is a classical problem in computer science. For some modern biological applications, computing the similarity between two objects might be very time consuming. For example, it takes a long time to compute the edit distance between two whole chromosomes and the alignment cost of two 3D protein structures. In this paper, we study the nearest neighbor search problem in metric space, where the pair-wise distance between two objects in the database is known and we want to minimize the number of distances computed on-line between the query and objects in the database in order to find the closest object. We have designed two randomized approaches for indexing metric space databases, where objects are purely described by their distances with each other. Analysis and experiments show that our approaches only need to compute O(log n) objects in order to find the closest object, where n is the total number of objects in the database.