Sciweavers

Share
KDD
2006
ACM

Mining distance-based outliers from large databases in any metric space

10 years 11 months ago
Mining distance-based outliers from large databases in any metric space
Let R be a set of objects. An object o R is an outlier, if there exist less than k objects in R whose distances to o are at most r. The values of k, r, and the distance metric are provided by a user at the run time. The objective is to return all outliers with the smallest I/O cost. This paper considers a generic version of the problem, where no information is available for outlier computation, except for objects' mutual distances. We prove an upper bound for the memory consumption which permits the discovery of all outliers by scanning the dataset 3 times. The upper bound turns out to be extremely low in practice, e.g., less than 1% of R. Since the actual memory capacity of a realistic DBMS is typically larger, we develop a novel algorithm, which integrates our theoretical findings with carefullydesigned heuristics that leverage the additional memory to improve I/O efficiency. Our technique reports all outliers by scanning the dataset at most twice (in some cases, even once), a...
Yufei Tao, Xiaokui Xiao, Shuigeng Zhou
Added 30 Nov 2009
Updated 30 Nov 2009
Type Conference
Year 2006
Where KDD
Authors Yufei Tao, Xiaokui Xiao, Shuigeng Zhou
Comments (0)
books