Taskbridge enables tabular anomaly detection without customized training
TaskBridge: Bridging Unsupervised Tabular Anomaly Detection and In-Context Learning via Virtual Tasks
Machine Learning
Summary
Finding unusual rows in tables of data is usually tricky and needs special training for each dataset. The authors developed TaskBridge, which turns the problem into a kind of supervised learning task using existing models. This means it can spot anomalies well without extra costly training or dataset-specific settings. They tested TaskBridge on hundreds of datasets, and it did better than many existing methods.
What this means in practice
- •For data science teams: Detect anomalies across diverse tabular datasets without retraining or tuning models for each new dataset.
- •For financial fraud analysts: Identify suspicious transactions efficiently by applying pretrained models with virtual tasks instead of building custom detectors.
Authors
Doyun Choi, Dooho Lee, Jaemin Yoo
Abstract
Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods rely on dataset-specific training and configuration search, recent tabular foundation models (TFMs) enable zero-shot anomaly detection on unseen datasets via in-context learning. Most TFM-based approaches, however, require anomaly-specific pretraining from scratch, making detection inherently dependent on synthetic TAD-specific priors and costly to update. Some approaches instead repurpose pretrained general-purpose TFMs for TAD to avoid this burden, but rely on computationally expensive formulations with restrictive anomaly inductive biases. In this work, we introduce TaskBridge, a new framework that efficiently repurposes pretrained general-purpose TFMs for unsupervised TAD by constructing virtual supervised tasks that directly recast anomaly detection as supervised in-context inference of TFMs. The resulting virtual tasks induce predictive structures under which normal queries and their target pairs receive high support, whereas anomalies tend to violate the induced structures and receive lower support, providing direct anomaly evidence. Across 790 real-world datasets, TaskBridge consistently outperforms 30 baselines, including state-of-the-art TFM-based approaches, without anomaly-specific TFM pretraining or dataset-specific model optimization.