Deep Structured Energy Based Models for Anomaly Detection

TL;DR

This paper introduces deep structured energy based models (DSEBMs) for anomaly detection, leveraging deep neural networks to model data distributions directly and employing score matching for efficient training across various data types.

Contribution

The paper presents novel DSEBMs that integrate energy-based models with deep architectures tailored for different data structures, using score matching for training without complex sampling.

Findings

DSEBMs outperform competing methods on benchmark tasks.

Energy score and reconstruction error are effective for anomaly detection.

The approach is applicable to static, sequential, and spatial data.

Abstract

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.