Discovering Anomalies on Mixed-Type Data Using a Generalized Student- t Based Approach
Feng Chen, Chang-Tien Lu
Abstract
Anomaly detection in mixed-type data is an important problem that has not been well addressed in the machine learning field. Existing approaches focus on computational efficiency and their correlation modeling between mixed-type attributes is heuristically driven, lacking a statistical foundation. In this paper, we propose MIxed-Type Robust dEtection (MITRE), a robust error buffering approach for anomaly detection in mixed-type datasets. Because of its non-Gaussian design, the problem is analytically intractable. Two novel Bayesian inference approaches are utilized to solve the intractable inferences: Integrated-nested Laplace Approximation (INLA), and Expectation Propagation (EP) with Variational Expectation-Maximization (EM). A set of algorithmic optimizations is implemented to improve the computational efficiency. A comprehensive suite of experiments was conducted on both synthetic and real world data to test the effectiveness and efficiency of MITRE.
People
Publication Details
- Date of publication:
- June 21, 2016
- Journal:
- IEEE Transactions on Knowledge and Data Engineering
- Page number(s):
- 2582-2595
- Volume:
- 28
- Issue Number:
- 10