A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text

TL;DR

This paper introduces a novel ensemble autoencoder method called RoSAE for detecting both independent and contextual text anomalies, demonstrating superior robustness and performance across multiple datasets.

Contribution

It proposes the TAC framework for contamination of inlier classes and introduces RoSAE, a new ensemble autoencoder approach for effective contextual anomaly detection in text.

Findings

Outperforms recent anomaly detection methods on multiple datasets.

Demonstrates robustness in detecting both independent and contextual anomalies.

Provides comprehensive evaluation across 8 datasets.

Abstract

Anomaly detection (AD) is a fast growing and popular domain among established applications like vision and time series. We observe a rich literature for these applications, but anomaly detection in text is only starting to blossom. Recently, self-supervised methods with self-attention mechanism have been the most popular choice. While recent works have proposed a working ground for building and benchmarking state of the art approaches, we propose two principal contributions in this paper: contextual anomaly contamination and a novel ensemble-based approach. Our method, Textual Anomaly Contamination (TAC), allows to contaminate inlier classes with either independent or contextual anomalies. In the literature, it appears that this distinction is not performed. For finding contextual anomalies, we propose RoSAE, a Robust Subspace Local Recovery Autoencoder Ensemble. All autoencoders of the ensemble present a different latent representation through local manifold learning. Benchmark shows that our approach outperforms recent works on both independent and contextual anomalies, while being more robust. We also provide 8 dataset comparison instead of only relying to Reuters and 20 Newsgroups corpora.