HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Explainable Anomaly Detection on High-Dimensional Time Series Data

Bijan Rad 1 Fei Song 1 Vincent Jacob 1 Yanlei Diao 1
1 CEDAR - Rich Data Analytics at Cloud Scale
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
Abstract : As enterprise information systems are collecting event streams from various sources, the ability of a system to automatically detect anomalous events and further provide human-readable explanations is of paramount importance. In this paper, we present an approach to integrated anomaly detection (AD) and explanation discovery (ED), which is able to leverage state-of-the-art Deep Learning (DL) techniques for anomaly detection, while being able to recover human-readable explanations for detected anomalies. At the core of the framework is a new human-interpretable dimensionality reduction (HIDR) method that not only reduces the dimensionality of the data, but also maintains a meaningful mapping from the original features to the transformed low-dimensional features. Such transformed features can be fed into any DL technique designed for anomaly detection, and the feature mapping will be used to recover human-readable explanations through a suite of new feature selection and explanation discovery methods. Evaluation using a recent explainable anomaly detection benchmark demonstrates the efficiency and effectiveness of HIDR for AD, and the result that while all three recent ED techniques failed to generate quality explanations on high-dimensional data, our HIDR-based ED framework can enable them to generate explanations with dramatic improvements in the quality of explanations and computational efficiency.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03522878
Contributor : Fei Song Connect in order to contact the contributor
Submitted on : Wednesday, January 12, 2022 - 12:17:57 PM
Last modification on : Friday, February 4, 2022 - 3:09:44 AM
Long-term archiving on: : Wednesday, April 13, 2022 - 8:03:47 PM

File

DEBS2021_HIDR.pdf
Files produced by the author(s)

Identifiers

Citation

Bijan Rad, Fei Song, Vincent Jacob, Yanlei Diao. Explainable Anomaly Detection on High-Dimensional Time Series Data. The 15th ACM International Conference on Distributed and Event-based Systems (DEBS ’21), Jun 2021, virtual event, Italy. ⟨10.1145/3465480.3468292⟩. ⟨hal-03522878⟩

Share

Metrics

Record views

43

Files downloads

80