Uncertainty-aware Evaluation of Auxiliary Anomalies with the Expected Anomaly Posterior
This addresses the challenge of poor-quality synthetic anomalies degrading anomaly detection performance, particularly in applications where real anomalies are scarce, though it is incremental as it builds on existing uncertainty-based methods.
The paper tackles the problem of evaluating the quality of synthetic anomalies used to train anomaly detectors, proposing the Expected Anomaly Posterior (EAP) to measure this quality based on uncertainty quantification. The result shows that EAP outperforms 12 adapted data quality estimators on 40 benchmark datasets of images and tabular data.
Anomaly detection is the task of identifying examples that do not behave as expected. Because anomalies are rare and unexpected events, collecting real anomalous examples is often challenging in several applications. In addition, learning an anomaly detector with limited (or no) anomalies often yields poor prediction performance. One option is to employ auxiliary synthetic anomalies to improve the model training. However, synthetic anomalies may be of poor quality: anomalies that are unrealistic or indistinguishable from normal samples may deteriorate the detector's performance. Unfortunately, no existing methods quantify the quality of auxiliary anomalies. We fill in this gap and propose the expected anomaly posterior (EAP), an uncertainty-based score function that measures the quality of auxiliary anomalies by quantifying the total uncertainty of an anomaly detector. Experimentally on 40 benchmark datasets of images and tabular data, we show that EAP outperforms 12 adapted data quality estimators in the majority of cases.