Disentangling Tabular Data Towards Better One-Class Anomaly Detection
This work addresses a domain-specific problem in tabular anomaly detection, offering a novel approach to improve detection accuracy for applications like fraud detection or system monitoring.
The paper tackles the challenge of one-class anomaly detection in tabular data by proposing a method to disentangle correlated attribute subsets, achieving an average improvement of 6.1% on AUC-PR and 2.1% on AUC-ROC over state-of-the-art methods across 20 datasets.
Tabular anomaly detection under the one-class classification setting poses a significant challenge, as it involves accurately conceptualizing "normal" derived exclusively from a single category to discern anomalies from normal data variations. Capturing the intrinsic correlation among attributes within normal samples presents one promising method for learning the concept. To do so, the most recent effort relies on a learnable mask strategy with a reconstruction task. However, this wisdom may suffer from the risk of producing uniform masks, i.e., essentially nothing is masked, leading to less effective correlation learning. To address this issue, we presume that attributes related to others in normal samples can be divided into two non-overlapping and correlated subsets, defined as CorrSets, to capture the intrinsic correlation effectively. Accordingly, we introduce an innovative method that disentangles CorrSets from normal tabular data. To our knowledge, this is a pioneering effort to apply the concept of disentanglement for one-class anomaly detection on tabular data. Extensive experiments on 20 tabular datasets show that our method substantially outperforms the state-of-the-art methods and leads to an average performance improvement of 6.1% on AUC-PR and 2.1% on AUC-ROC. Codes are available at https://github.com/yjnanan/Disent-AD.