Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2016

Abstract

This paper introduces a novel unsupervised outlier detection method, namely Coupled Biased Random Walks (CBRW), for identifying outliers in categorical data with diversified frequency distributions and many noisy features. Existing pattern-based outlier detection methods are ineffective in handling such complex scenarios, as they misfit such data. CBRW estimates outlier scores of feature values by modelling feature value level couplings, which carry intrinsic data characteristics, via biased random walks to handle this complex data. The outlier scores of feature values can either measure the outlierness of an object or facilitate the existing methods as a feature weighting and selection indicator. Substantial experiments show that CBRW can not only detect outliers in complex data significantly better than the state-of-the-art methods, but also greatly improve the performance of existing methods on data sets with many noisy features.

Discipline

Databases and Information Systems | Data Storage Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, New York, 2016 July 9-15

First Page

1902

Last Page

1908

Identifier

10.5555/3060832.3060887

Publisher

ACM

City or Country

New York

Share

COinS