CORE: In-Context Reconstruction for Unified Tabular Anomaly Detection

2026-07-29

AI Summary

This work addresses the challenges in unified tabular anomaly detection—namely, the difficulty of aligning heterogeneous data, the susceptibility to semantic information loss, and the reliance on anomaly labels or synthetic data—by formally framing the task as an unsupervised context reconstruction problem. It introduces a decorrelated feature alignment mechanism that enables cross-dataset alignment while preserving original semantics, and employs a context-driven reconstruction model that learns the input distribution exclusively from normal samples to identify anomalies. Requiring neither anomaly annotations nor synthetic data, the proposed method significantly outperforms existing unified tabular anomaly detection approaches across multiple unseen tabular datasets, achieving efficient, accurate, and highly generalizable anomaly detection.

Abstract

Tabular anomaly detection (TAD), which focuses on identifying abnormal samples that deviate from the majority in tabular data, has received growing attention. Recently, there has been an emerging trend towards unified TAD, which seeks to detect anomalies across different datasets using a single generalizable model. In unified TAD, aligning heterogeneous data remains challenging. While existing methods often rely on distance-based unified feature construction, they may obscure the semantics of the original features. Moreover, existing approaches typically formulate anomaly detection as a binary classification task, which may overlook diverse anomaly patterns from various datasets and be misled by unrepresentative synthetic anomalies. To address these challenges, we propose an in-COntext REconstruction approach for unified TAD (CORE for short). It introduces a decorrelated feature alignment module to directly align heterogeneous features into a unified representation space, which retains their semantic information. Meanwhile, CORE formulates unified TAD as an in-context reconstruction problem, eliminating the need for labeled or synthesized anomalies. Specifically, the in-context reconstruction module reconstructs each sample by leveraging contextual normal samples to capture dataset-specific distributions, such that reconstruction errors reflect its deviation from normality, facilitating unified TAD on arbitrary unseen datasets.

Problem

• tabular anomaly detection
• unified model
• heterogeneous data alignment
• anomaly pattern diversity
• synthetic anomalies

Innovation

• in-context reconstruction
• feature alignment
• unified tabular anomaly detection
• semantic preservation
• unsupervised anomaly detection