Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation

TL;DR

The paper introduces PLAG, a pseudo-label-guided anomaly generation method that enhances tabular anomaly detection by focusing on localized feature abnormalities and filtering synthetic anomalies for improved detection accuracy.

Contribution

It presents a novel framework that leverages pseudo-anomalies and a two-stage data selection strategy to improve detection performance without requiring ground-truth labels.

Findings

PLAG achieves state-of-the-art results on eight benchmarks.

Integrating PLAG boosts existing detectors' F1-scores by 0.08 to 0.21.

The method effectively captures localized anomaly patterns in tabular data.

Abstract

Identifying anomalous instances in tabular data is essential for improving data reliability and maintaining system stability. Due to the scarcity of ground-truth anomaly labels, existing methods mainly rely on unsupervised anomaly detection models, or exploit a small number of labeled anomalies to facilitate detection via sample generation or contrastive learning. However, unsupervised methods lack sufficient anomaly awareness, while current generation and contrastive approaches tend to compute anomalies globally, overlooking the localized anomaly patterns of tabular features, resulting in suboptimal detection performance. To address these limitations, we propose PLAG, a pseudo-label-guided anomaly generation method designed to enhance tabular anomaly detection. Specifically, by utilizing pseudo-anomalies as guidance signals and decoupling the overall anomaly quantification of a sample into an accumulation of feature-level abnormalities, PLAG not only effectively obviates the need for scarce ground-truth labels but also provides a novel perspective for the model to comprehend localized anomalous signals at a fine-grained level. Furthermore, a two-stage data selection strategy is proposed, integrating format verification and uncertainty estimation to rigorously filter candidate samples, thereby ensuring the fidelity and diversity of the synthetic anomalies. Ultimately, these filtered synthetic anomalies serve as robust discriminative guidance, empowering the model to better separate normal and anomalous instances. Extensive experiments demonstrate that PLAG achieves state-of-the-art performance against eight representative baselines. Moreover, as a flexible framework, it integrates seamlessly with existing unsupervised detectors, consistently boosting F1-scores by 0.08 to 0.21.