Deep Active Learning for Anomaly Detection

TL;DR

This paper introduces a novel active learning layer for deep unsupervised anomaly detection models, enabling effective separation of outliers with minimal prior assumptions, validated on synthetic and real datasets.

Contribution

We propose a new active learning layer that can be integrated into existing deep anomaly detection models to improve outlier identification.

Findings

Effective detection of clustered anomalies

Improved performance on low-density anomalies

Compatible with various deep learning architectures

Abstract

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through appropriate expert feedback. Thus, in this work we present an active learning method that can be built upon existing deep learning solutions for unsupervised anomaly detection, so that outliers can be separated from normal data effectively. We introduce a new layer that can be easily attached to any deep learning model designed for unsupervised anomaly detection to transform it into an active method. We report results on both synthetic and real anomaly detection datasets, using multi-layer perceptrons and autoencoder architectures empowered with the proposed active layer, and we discuss their performance on finding clustered and low density anomalies.