SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction

2026/02/04 by Yanan He, Yunshi Wen, Xin Wang +1
#cs.LG

paper · pdf

Abstract

Time-series anomaly prediction aims to forecast future system failures before they fully emerge, making latent predictive models such as JEPA a promising framework for capturing precursor dynamics. However, directly applying continuous self-distillation to time-series data is often unstable and can lead to representation collapse, while also struggling to model precursors evolving at different temporal scales. To address this, we propose SC-JEPA, a new JEPA-based framework to model time-series anomaly prediction in a discretized predictive state space. It introduces a soft codebook bottleneck to stabilize latent predictive learning and encourage regime-level structure in the learned representations. Building on this stabilized latent space, we further design a multi-resolution predictive objective to capture precursor patterns at different temporal scales. Experiments on five real-world benchmarks show that SC-JEPA achieves strong and consistent early-warning performance.

Citations

• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Related

• Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling
• Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning
• Forecast2Anomaly (F2A): Adapting Multivariate Time Series Foundation Models for Anomaly Prediction
• When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
• A Predictive Approach To Enhance Time-Series Forecasting