CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection

TL;DR

CEDL introduces a unified, geometry-aware supervised anomaly detection framework that embeds normality directly into the discriminative learning process, enabling interpretable scoring across diverse data types.

Contribution

It proposes a novel end-to-end method that integrates geometric normality into discriminative learning, improving anomaly detection interpretability and performance.

Findings

Achieves competitive results on tabular, time-series, and image data.

Provides interpretable anomaly scores without post-hoc calibration.

Demonstrates broad applicability across real-world datasets.

Abstract

Supervised anomaly detection methods perform well in identifying known anomalies that are well represented in the training set. However, they often struggle to generalise beyond the training distribution due to decision boundaries that lack a clear definition of normality. Existing approaches typically address this by regularising the representation space during training, leading to separate optimisation in latent and label spaces. The learned normality is therefore not directly utilised at inference, and their anomaly scores often fall within arbitrary ranges that require explicit mapping or calibration for probabilistic interpretation. To achieve unified learning of geometric normality and label discrimination, we propose Centre-Enhanced Discriminative Learning (CEDL), a novel supervised anomaly detection framework that embeds geometric normality directly into the discriminative objective. CEDL reparameterises the conventional sigmoid-derived prediction logit through a centre-based radial distance function, unifying geometric and discriminative learning in a single end-to-end formulation. This design enables interpretable, geometry-aware anomaly scoring without post-hoc thresholding or reference calibration. Extensive experiments on tabular, time-series, and image data demonstrate that CEDL achieves competitive and balanced performance across diverse real-world anomaly detection tasks, validating its effectiveness and broad applicability.