Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data

TL;DR

This paper introduces DDAE, a novel diffusion-scheduled denoising autoencoder framework that enhances anomaly detection in tabular data by integrating diffusion noise scheduling and contrastive learning, outperforming existing models.

Contribution

The paper presents DDAE, combining diffusion-based noise scheduling with contrastive learning, offering a new approach for more effective anomaly detection in tabular data.

Findings

DDAE outperforms state-of-the-art autoencoder models in semi-supervised settings.

Higher noise levels improve unsupervised training performance.

Lower noise with linear scheduling is optimal for semi-supervised learning.

Abstract

Anomaly detection in tabular data remains challenging due to complex feature interactions and the scarcity of anomalous examples. Denoising autoencoders rely on fixed-magnitude noise, limiting adaptability to diverse data distributions. Diffusion models introduce scheduled noise and iterative denoising, but lack explicit reconstruction mappings. We propose the Diffusion-Scheduled Denoising Autoencoder (DDAE), a framework that integrates diffusion-based noise scheduling and contrastive learning into the encoding process to improve anomaly detection. We evaluated DDAE on 57 datasets from ADBench. Our method outperforms in semi-supervised settings and achieves competitive results in unsupervised settings, improving PR-AUC by up to 65% (9%) and ROC-AUC by 16% (6%) over state-of-the-art autoencoder (diffusion) model baselines. We observed that higher noise levels benefit unsupervised training, while lower noise with linear scheduling is optimal in semi-supervised settings. These findings underscore the importance of principled noise strategies in tabular anomaly detection.