Deep Structured Energy Based Models for Anomaly Detection
This work addresses anomaly detection for applications with structured data, but it is incremental as it builds on existing energy-based models and score matching techniques.
The paper tackles anomaly detection by modeling data distributions with deep structured energy-based models (DSEBMs), integrating them with various data types and using score matching for training, and shows that the model consistently matches or outperforms competing methods on benchmark tasks.
In this paper, we attack the anomaly detection problem by directly modeling the data distribution with deep architectures. We propose deep structured energy based models (DSEBMs), where the energy function is the output of a deterministic deep neural network with structure. We develop novel model architectures to integrate EBMs with different types of data such as static data, sequential data, and spatial data, and apply appropriate model architectures to adapt to the data structure. Our training algorithm is built upon the recent development of score matching \cite{sm}, which connects an EBM with a regularized autoencoder, eliminating the need for complicated sampling method. Statistically sound decision criterion can be derived for anomaly detection purpose from the perspective of the energy landscape of the data distribution. We investigate two decision criteria for performing anomaly detection: the energy score and the reconstruction error. Extensive empirical studies on benchmark tasks demonstrate that our proposed model consistently matches or outperforms all the competing methods.