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

• URL: http://arxiv.org/abs/2604.20255v1
• Date: Wed, 22 Apr 2026 07:04:08 GMT
• Title: uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFN
• Abstract summary: We propose uLEAD-TabPFN, a dependency-based anomaly detection framework built on Prior-Data Fitted Networks (PFNs)<n>i.e., it identifies anomalies as violations of conditional dependencies in a learned latent space, leveraging frozen PFNs for dependency estimation.<n>i.e., it achieves strong performance in medium- and high-dimensional settings, where it attains the top average rank.
• Score: 26.03194873655899
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Towards Anomaly Detection on Relational Data [51.473064583839296]
  We propose a reconstruction-based framework that captures anomalies from both attribute and relational edge reconstruction.<n>RelAD consistently outperforms other baselines while achieving competitive efficiency.
  arXiv  Detail & Related papers  (2026-06-17T02:36:32Z)
• TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data [11.770179526235511]
  We propose a continual learning (CL) method to continually learn from different tasks.<n>Our method consists of three main parts: our AGF model, Taskfusion augmentation, and outlier exposure.<n>We evaluate the approach on 21 heterogeneous datasets across multiple domains.
  arXiv  Detail & Related papers  (2026-06-10T09:21:28Z)
• TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection [15.271061413934332]
  Two-stage pseudo anomaly-guided anomaly detection method is proposed.<n>Method generates pseudo-anomalous windows near the normal boundary.<n>It learns anomaly-sensitive representations through contrastive learning between normal and pseudo-anomalous windows.
  arXiv  Detail & Related papers  (2026-06-02T15:39:10Z)
• Towards One-for-All Anomaly Detection for Tabular Data [87.63505963517512]
  Tabular anomaly detection (TAD) is critical in many real-world applications.<n>We propose OFA-TAD, a framework that only requires one-time training on multiple source datasets.<n>Experiments on 34 datasets from 14 domains demonstrate that OFA-TAD achieves superior anomaly detection performance.
  arXiv  Detail & Related papers  (2026-03-15T14:42:05Z)
• HMVI: Unifying Heterogeneous Attributes with Natural Neighbors for Missing Value Inference [1.0577954299884882]
  Current imputation methods handle numerical and categorical attributes independently, overlooking critical interdependencies among heterogeneous features.<n>We propose a novel imputation approach that explicitly models cross-type feature dependencies within a unified framework.
  arXiv  Detail & Related papers  (2026-01-08T15:18:36Z)
• Unified Unsupervised Anomaly Detection via Matching Cost Filtering [113.43366521994396]
  Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data.<n>We present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model.
  arXiv  Detail & Related papers  (2025-10-03T03:28:18Z)
• CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection [49.11819337853632]
  Anomaly detection is a complex problem due to the ambiguity in defining anomalies, the diversity of anomaly types, and the scarcity of training data.<n>We propose CLIPfusion, a method that leverages both discriminative and generative foundation models.<n>We believe that our method underscores the effectiveness of multi-modal and multi-model fusion in tackling the multifaceted challenges of anomaly detection.
  arXiv  Detail & Related papers  (2025-06-13T13:30:15Z)
• Tab-Shapley: Identifying Top-k Tabular Data Quality Insights [7.666573679741346]
  We introduce Tab-Shapley, a cooperative game theory based framework that uses Shapley values to quantify the contribution of each attribute to the data's anomalous nature.<n>While calculating Shapley values typically requires exponential time, we show that our game admits a closed-form solution, making the computation efficient.
  arXiv  Detail & Related papers  (2025-01-12T02:24:55Z)
• FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Data [11.42231457116486]
  FedAD-Bench is a benchmark for evaluating unsupervised anomaly detection algorithms within the context of federated learning. We identify key challenges such as model aggregation inefficiencies and metric unreliability. Our work aims to establish a standardized benchmark to guide future research and development in federated anomaly detection.
  arXiv  Detail & Related papers  (2024-08-08T13:14:19Z)
• Unraveling the "Anomaly" in Time Series Anomaly Detection: A Self-supervised Tri-domain Solution [89.16750999704969]
  Anomaly labels hinder traditional supervised models in time series anomaly detection. Various SOTA deep learning techniques, such as self-supervised learning, have been introduced to tackle this issue. We propose a novel self-supervised learning based Tri-domain Anomaly Detector (TriAD)
  arXiv  Detail & Related papers  (2023-11-19T05:37:18Z)
• Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection [37.99031842449251]
  Video anomaly detection under weak supervision presents significant challenges. We present a weakly supervised anomaly detection framework that focuses on efficient context modeling and enhanced semantic discriminability. Our approach significantly improves the detection accuracy of certain anomaly sub-classes, underscoring its practical value and efficacy.
  arXiv  Detail & Related papers  (2023-06-26T06:45:16Z)
• Dependency-based Anomaly Detection: a General Framework and Comprehensive Evaluation [33.31923133201812]
  This paper introduces Dependency-based Anomaly Detection (DepAD) DepAD reframes unsupervised anomaly detection as supervised feature selection and prediction tasks. Two DepAD algorithms emerge as all-rounders and superior performers in handling a wide range of datasets.
  arXiv  Detail & Related papers  (2020-11-13T01:39:44Z)
• TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks [73.01104041298031]
  TadGAN is an unsupervised anomaly detection approach built on Generative Adversarial Networks (GANs) To capture the temporal correlations of time series, we use LSTM Recurrent Neural Networks as base models for Generators and Critics. To demonstrate the performance and generalizability of our approach, we test several anomaly scoring techniques and report the best-suited one.
  arXiv  Detail & Related papers  (2020-09-16T15:52:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.