Skip to content

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

Sep 2026 · arXiv.org · Vol abs/2609.33610 · 0 citations · 43 references
Computer Science

TL;DR

Experiments 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.

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.

View source

Similar papers

LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection

Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations. Language-derived semantics offer complementary context, but existing multimodal approaches may rely on time-associated paired textual information that is difficult to obtain consist...

Jahyeob Koo, Kio Yun, Byoung-Mo Koo et al. · 0 citations
Open access Sep 2026

Anomaly Detection in Long-term Time Series with Transformer and Variational Autoencoder

Transformer with Variational AutoEncoder is presented, a framework that combines a dual-embedding representation pipeline, a Transformer encoder for long-range dependency modeling, and VAE-based latent regularization of encoded features to provide an effective and robust solution for long-term time-series anomaly detec...

Xian-Kun Shi, Yi-Bo Li, Zi-Qi Wang et al. · 0 citations
#machine learning Preprint Aug 2026

CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation

CAST is proposed, a Context- and Anomaly Structure-conditioned Time series anomaly generation framework with principled two-stage pretraining and finetuning strategy that consistently outperforms state-of-the-art anomaly generation methods in terms of both generation fidelity and downstream task utility.

H. Zhang, Jie Peng, Song-Yuan Sui et al. · 0 citations
Open access 2026

CHAIN: Long-Context History-Supervised Multivariate Time Series Anomaly Detection

This paper proposes CHAIN (long-Context History-supervised Anomaly detectIoN), a novel framework that explicitly captures long-term historical contexts under anomaly simulation and supervises current-window anomaly detection via masked cross-attention fusion.

Eunji Jun, Junho Yim · 0 citations
Conference Open access Sep 2026

Multi-View Ensemble for Time Series Anomaly Detection via Coupling Flows

Time series anomaly detection faces a critical challenge that different anomaly types require different detection mechanisms, yet single methods are inherently limited by their design biases. We propose FlowFuse, a multi-view ensemble framework with coupling flow-based score fusion for time series anomaly detection. Fl...

Wanghui Qiu, Chen-Xi Liu, Shiyan Hu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection

In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Some vision-language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these de...

Meng-Yang Zhao, Teng Fu, Hai-Yang Yu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.