Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing

2026-09-27

AI Summary

This study addresses the supervision deficiency in time-series anomaly detection caused by label scarcity and context dependency by proposing the CAPS framework. This method introduces a novel supervision recovery mechanism that requires no target-domain labels, reconstructing supervisory signals through simulated normal-anomalous pairings. By integrating deep reconstruction, background consistency constraints, dual intra-counterfactual recombination, and multi-modal prior sampling, CAPS learns semantic representations and generates context-anchored contrastive samples to train a discriminative detector. Experimental results demonstrate that CAPS achieves state-of-the-art performance across four metrics on nine datasets, effectively validating the superiority of context anchoring and continuous anomalous semantic space construction.

Abstract

Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised objectives or surrogate abnormal patterns, providing limited supervision for context-dependent normal--anomalous distinctions. We propose Context-Anchored Pair Supervision (CAPS), a supervision-recovery framework for TSAD. CAPS views ideal anomaly supervision as a matched comparison between normal and anomalous outcomes under the same temporal context, and seeks to recover such supervision without target-domain anomaly labels. Using simulated normal--anomalous pairs, CAPS learns structure and anomaly-semantic representations through reconstruction, background consistency, and within-pair counterfactual recombination. The resulting anomaly representations form a continuous semantic space with coarse modes and induce a sampleable multimodal prior. CAPS conditionally realizes sampled semantics as residual-form effects on target reference trajectories. The resulting context-anchored normal--anomalous counterparts provide temporal supervision for discriminative detector learning. Experiments on nine datasets show that CAPS achieves the strongest aggregate performance across all four evaluation metrics among the compared methods, while complementary ablations and transfer analyses support the roles of context anchoring, semantic disentanglement, and conditional realization.

Problem

• Time Series Anomaly Detection
• Supervision Recovery
• Context-Dependent Anomalies
• Label Scarcity

Innovation

• Time Series Anomaly Detection
• Context-Anchored Pairing
• Supervision Recovery
• Counterfactual Recombination
• Semantic Disentanglement