Robust Manifold Learning via Conformity Pursuit
- 14 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (3) , 425-429
Abstract
This paper presents an effective and simple method, termed Global Conformity Pursuit (GCP), for robust manifold learning. Data points lying on a union of low-dimensional non-linear manifolds are expected to be highly conforming. On the other hand, outliers do not typically adhere to low-dimensional structures or otherwise do not exist in large numbers. Hence, they can be identified by their low overall resemblance to the rest of the data. Our kernel-based setting allows us to capture the underlying non-linear structure of the manifold data, while avoiding the construction of local neighborhood regions which typically causes extreme sensitivity to noise and outliers. Aside from its significantly simple structure – involving only a matrix evaluation and multiplication – GCP is the first manifold learning approach that is simultaneously non-iterative and capable of tolerating a large number of outliers, dependent outliers and noise components. Theoretical analysis guarantees a large gap between conformity values of inliers and outliers. Experimental results showcase potential uses of the proposed framework on benchmark datasets.Keywords
Funding Information
- NSF (CCF-1552497)
- NSF (1643835, 1161228, 1356233)
- CSIT TEAm BOG
This publication has 23 references indexed in Scilit:
- A survey of anomaly detection techniques in financial domainFuture Generation Computer Systems, 2016
- Robust Subspace Clustering via ThresholdingIEEE Transactions on Information Theory, 2015
- Outlier Detection in the Framework of Dimensionality ReductionInternational Journal of Pattern Recognition and Artificial Intelligence, 2015
- An Outlier Detection Method for Robust Manifold Learning2013
- Outlier detection for patient monitoring and alertingJournal of Biomedical Informatics, 2013
- Local anomaly descriptor2012
- Robust kernel principal component analysis and classificationAdvances in Data Analysis and Classification, 2010
- Clustering through ranking on manifolds2005
- Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold LearningIEEE Transactions on Signal Processing, 2004
- Outlier detection for high dimensional dataACM SIGMOD Record, 2001