Investigating Mask-aware Prototype Learning for Tabular Anomaly Detection

TL;DR

This paper introduces a novel mask-aware prototype learning approach for tabular anomaly detection, enhancing representation disentanglement and global correlation modeling to improve detection accuracy and interpretability.

Contribution

It proposes a new method combining mask modeling and prototype learning with optimal transport, addressing representation entanglement and correlation modeling issues in tabular anomaly detection.

Findings

Outperforms existing methods on 20 benchmark datasets.

Improves interpretability of anomaly detection results.

Demonstrates effective disentangled representation learning.

Abstract

Tabular anomaly detection, which aims at identifying deviant samples, has been crucial in a variety of real-world applications, such as medical disease identification, financial fraud detection, intrusion monitoring, etc. Although recent deep learning-based methods have achieved competitive performances, these methods suffer from representation entanglement and the lack of global correlation modeling, which hinders anomaly detection performance. To tackle the problem, we incorporate mask modeling and prototype learning into tabular anomaly detection. The core idea is to design learnable masks by disentangled representation learning within a projection space and extracting normal dependencies as explicit global prototypes. Specifically, the overall model involves two parts: (i) During encoding, we perform mask modeling in both the data space and projection space with orthogonal basis vectors for learning shared disentangled normal patterns; (ii) During decoding, we decode multiple masked representations in parallel for reconstruction and learn association prototypes to extract normal characteristic correlations. Our proposal derives from a distribution-matching perspective, where both projection space learning and association prototype learning are formulated as optimal transport problems, and the calibration distances are utilized to refine the anomaly scores. Quantitative and qualitative experiments on 20 tabular benchmarks demonstrate the effectiveness and interpretability of our model.