uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFN

TL;DR

uLEAD-TabPFN introduces a scalable, uncertainty-aware, dependency-based anomaly detection framework for high-dimensional tabular data using Prior-Data Fitted Networks, outperforming existing methods.

Contribution

The paper presents uLEAD-TabPFN, a novel dependency-based anomaly detection method leveraging PFNs for robust, scalable detection in complex, high-dimensional tabular datasets.

Findings

Achieves top average rank on 57 ADBench datasets.

Improves ROC-AUC by nearly 20% over baselines on high-dimensional data.

Provides complementary detection capabilities on challenging datasets.

Abstract

Anomaly detection in tabular data is challenging due to high dimensionality, complex feature dependencies, and heterogeneous noise. Many existing methods rely on proximity-based cues and may miss anomalies caused by violations of complex feature dependencies. Dependency-based anomaly detection provides a principled alternative by identifying anomalies as violations of dependencies among features. However, existing methods often struggle to model such dependencies robustly and to scale to high-dimensional data with complex dependency structures. To address these challenges, we propose uLEAD-TabPFN, a dependency-based anomaly detection framework built on Prior-Data Fitted Networks (PFNs). uLEAD-TabPFN identifies anomalies as violations of conditional dependencies in a learned latent space, leveraging frozen PFNs for dependency estimation. Combined with uncertainty-aware scoring, the proposed framework enables robust and scalable anomaly detection. Experiments on 57 tabular datasets from ADBench show that uLEAD-TabPFN achieves particularly strong performance in medium- and high-dimensional settings, where it attains the top average rank. On high-dimensional datasets, uLEAD-TabPFN improves the average ROC-AUC by nearly 20\% over the average baseline and by approximately 2.8\% over the best-performing baseline, while maintaining overall superior performance compared to state-of-the-art methods. Further analysis shows that uLEAD-TabPFN provides complementary anomaly detection capability, achieving strong performance on datasets where many existing methods struggle.