Timezone: »

Exploiting Variable Correlation with Masked Modeling for Anomaly Detection in Time Series
Panagiotis Lymperopoulos · Yukun Li · Liping Liu
Event URL: https://openreview.net/forum?id=TCJuzs585W »

Online anomaly detection in multi-variate time series is a challenging problem particularly when there is no supervision information. Autoregressive predictive models are often used for this task, but such detection methods often overlook correlations between variables observed in the most recent step and thus miss some anomalies that violate normal variable relations. In this work, we propose a masked modeling approach that captures variable relations and temporal relations in a single predictive model. Our method can be combined with a wide range of predictive models. Our experiment shows that our new masked modeling method improves detection performance over pure autoregressive models when the time series itself is not very predictable.

Author Information

Panagiotis Lymperopoulos (Tufts University)
Panagiotis Lymperopoulos

This is the personal website of Panagiotis Lymperopoulos. I am a PhD Candidate at Tufts University in the Department of Computer Science. I am a member of the Tufts Machine Learning Group and my advisor is Prof. Liping Liu. Currently, I am pursuing research ideas in the intersection of machine learning and logical reasoning. In the past I have worked on anomaly detection, the application of machine learning to biological data and natural language processing.

Yukun Li (Tufts University)
Liping Liu (Tufts University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors