Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
It addresses anomaly detection for unstructured textual data, a less attended area compared to structured data, with incremental improvements in method.
The paper tackles textual anomaly detection by proposing a deep anomaly-injected support vector data description (AI-SVDD) framework that learns compact data representations and uses known anomalies to improve discrimination, showing promising results and outperforming existing works on three applications with multiple datasets.
Anomaly detection or outlier detection is a common task in various domains, which has attracted significant research efforts in recent years. Existing works mainly focus on structured data such as numerical or categorical data; however, anomaly detection on unstructured textual data is less attended. In this work, we target the textual anomaly detection problem and propose a deep anomaly-injected support vector data description (AI-SVDD) framework. AI-SVDD not only learns a more compact representation of the data hypersphere but also adopts a small number of known anomalies to increase the discriminative power. To tackle text input, we employ a multilayer perceptron (MLP) network in conjunction with BERT to obtain enriched text representations. We conduct experiments on three text anomaly detection applications with multiple datasets. Experimental results show that the proposed AI-SVDD is promising and outperforms existing works.