Search papers, labs, and topics across Lattice.
This paper introduces uLEAD-TabPFN, a dependency-based anomaly detection framework for tabular data that uses Prior-Data Fitted Networks (PFNs) to model conditional dependencies in a learned latent space. Anomalies are identified as violations of these learned dependencies, enhanced by uncertainty-aware scoring for robustness. Experiments on 57 ADBench datasets demonstrate that uLEAD-TabPFN achieves state-of-the-art performance, particularly in medium- and high-dimensional settings, improving ROC-AUC by nearly 20% over the average baseline in high-dimensional datasets.
Tabular anomaly detection gets a serious upgrade: uLEAD-TabPFN leverages frozen PFNs to model complex feature dependencies, outperforming existing methods by a significant margin, especially in high-dimensional spaces.
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.
