Towards One-for-All Anomaly Detection for Tabular Data

2026-03-15

AI Summary

This work proposes OFA-TAD, the first universal framework for tabular anomaly detection that overcomes the limitations of existing “one-dataset-one-model” approaches, which suffer from poor generalization and high computational costs. OFA-TAD enables plug-and-play anomaly detection on unseen domains through a single joint training phase across multiple source datasets. The framework integrates multi-view neighborhood distance representations, metric space transformation, a Mixture-of-Experts scoring network, and an entropy-regularized gating mechanism, further enhanced by multi-strategy synthetic anomalies to improve robustness. Extensive experiments across 34 datasets spanning 14 distinct domains demonstrate that OFA-TAD significantly outperforms current methods under a strict one-time training protocol, exhibiting exceptional cross-domain generalization capability.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Tabular anomaly detection (TAD) aims to identify samples that deviate from the majority in tabular data and is critical in many real-world applications. However, existing methods follow a ``one model for one dataset (OFO)'' paradigm, which relies on dataset-specific training and thus incurs high computational cost and yields limited generalization to unseen domains. To address these limitations, we propose OFA-TAD, a generalist one-for-all (OFA) TAD framework that only requires one-time training on multiple source datasets and can generalize to unseen datasets from diverse domains on-the-fly. To realize one-for-all tabular anomaly detection, OFA-TAD extracts neighbor-distance patterns as transferable cues, and introduces multi-view neighbor-distance representations from multiple transformation-induced metric spaces to mitigate the transformation sensitivity of distance profiles. To adaptively combine multi-view distance evidence, a Mixture-of-Experts (MoE) scoring network is employed for view-specific anomaly scoring and entropy-regularized gated fusion, with a multi-strategy anomaly synthesis mechanism to support training under the one-class constraint. Extensive experiments on 34 datasets from 14 domains demonstrate that OFA-TAD achieves superior anomaly detection performance and strong cross-domain generalizability under the strict OFA setting.

Problem

• tabular anomaly detection
• one-for-all
• cross-domain generalization
• computational cost
• generalizability

Innovation

• one-for-all anomaly detection
• tabular data
• multi-view neighbor-distance representation
• Mixture-of-Experts
• cross-domain generalization