ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
This provides a unified framework for tabular anomaly detection, addressing the limitation of existing methods that are specific to single supervision regimes.
The paper tackled the problem of tabular anomaly detection across different supervision regimes by proposing ICLAD, an in-context learning foundation model that generalizes across datasets and regimes, achieving state-of-the-art performance on 57 datasets from ADBench.
Anomaly detection on tabular data is commonly studied under three supervision regimes, including one-class settings that assume access to anomaly-free training samples, fully unsupervised settings with unlabeled and potentially contaminated training data, and semi-supervised settings with limited anomaly labels. Existing deep learning approaches typically train dataset-specific models under the assumption of a single supervision regime, which limits their ability to leverage shared structures across anomaly detection tasks and to adapt to different supervision levels. We propose ICLAD, an in-context learning foundation model for tabular anomaly detection that generalizes across both datasets and supervision regimes. ICLAD is trained via meta-learning on synthetic tabular anomaly detection tasks, and at inference time, the model assigns anomaly scores by conditioning on the training set without updating model weights. Comprehensive experiments on 57 tabular datasets from ADBench show that our method achieves state-of-the-art performance across three supervision regimes, establishing a unified framework for tabular anomaly detection.