Enhancing Unsupervised Anomaly Detection with Score-Guided Network
This addresses challenges in unsupervised anomaly detection for applications like healthcare and finance, but it is incremental as it builds on existing methods like autoencoders.
The paper tackled the problem of distinguishing normal from abnormal data in unsupervised anomaly detection, especially in transition fields where they are mixed, by proposing a score-guided network and regularization to enlarge anomaly score disparities, resulting in state-of-the-art performance on synthetic and real-world datasets.
Anomaly detection plays a crucial role in various real-world applications, including healthcare and finance systems. Owing to the limited number of anomaly labels in these complex systems, unsupervised anomaly detection methods have attracted great attention in recent years. Two major challenges faced by the existing unsupervised methods are: (i) distinguishing between normal and abnormal data in the transition field, where normal and abnormal data are highly mixed together; (ii) defining an effective metric to maximize the gap between normal and abnormal data in a hypothesis space, which is built by a representation learner. To that end, this work proposes a novel scoring network with a score-guided regularization to learn and enlarge the anomaly score disparities between normal and abnormal data. With such score-guided strategy, the representation learner can gradually learn more informative representation during the model training stage, especially for the samples in the transition field. We next propose a score-guided autoencoder (SG-AE), incorporating the scoring network into an autoencoder framework for anomaly detection, as well as other three state-of-the-art models, to further demonstrate the effectiveness and transferability of the design. Extensive experiments on both synthetic and real-world datasets demonstrate the state-of-the-art performance of these score-guided models (SGMs).