From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection

TL;DR

OUTFORMER is a novel foundation model for tabular outlier detection that leverages synthetic training data and in-context learning to enable fast, zero-shot, plug-and-play deployment with state-of-the-art performance.

Contribution

It introduces OUTFORMER, which advances prior work by combining synthetic priors and curriculum training for zero-shot outlier detection.

Findings

Achieves state-of-the-art results on AdBench.

Performs well on two new large-scale benchmarks.

Enables fast, zero-shot inference without additional training.

Abstract

Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard. Foundation models (FMs) have transformed ML, and OD is no exception: Shen et. al. (2025) introduced FoMo-0D, the first FM for OD, achieving remarkable performance against numerous baselines. This work introduces OUTFORMER, which advances FoMo-0D with (1) a mixture of synthetic priors and (2) self-evolving curriculum training. OUTFORMER is pretrained solely on synthetic labeled datasets and infers test labels of a new task by using its training data as in-context input. Inference is fast and zero-shot, requiring merely forward pass and no labeled outliers. Thanks to in-context learning, it requires zero additional work-no OD model training or bespoke model selection-enabling truly plug-and-play deployment. OUTFORMER achieves state-of-the-art performance on the prominent AdBench, as well as two new large-scale OD benchmarks that we introduce, comprising over 1,500 datasets, while maintaining speedy inference.