analiza aiqbench
NeuCoReClass AD advances self-supervised learning for time series anomaly detection by integrating multiple proxy tasks to improve generalization without labeled data. The approach leverages neural transformation learning to create diverse augmented views, outperforming classical baselines and other deep-learning models across various benchmarks. This work is significant for practitioners seeking robust unsupervised methods that can characterize distinct anomaly profiles in complex temporal datasets.
NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detection
arXiv:2508.00909v2 Announce Type: replace Abstract: Time series anomaly detection plays a critical role in a wide range of real-world applications. Among unsupervised approaches, self-supervised learning has gained traction for modeling normal behavior without the need of labeled data. However, many existing methods rely on a single proxy task, limiting their ability to capture meaningful patterns in normal data. Moreover, they often depend on handcrafted transformations tailored specific domains, hindering their generalization accross diverse problems. To address these limitations, we introduce NeuCoReClass AD, a self-supervised multi-task time series anomaly detection framework that combines contrastive, reconstruction, and classification proxy tasks. Our method employs neural transformation learning to generate augmented views that are informative, diverse, and coherent, without requiring domain-specific knowledge. We evaluate NeuCoReClass AD across a wide range of benchmarks, demonstrating that it consistently outperforms both classical baselines and most deep-learning alternatives. Furthermore, it enables the characterization of distinct anomaly profiles in a fully unsupervised manner.
Abstract:Time series anomaly detection plays a critical role in a wide range of real-world applications. Among unsupervised approaches, self-supervised learning has gained traction for modeling normal behavior without the need of labeled data. However, many existing methods rely on a single proxy task, limiting their ability to capture meaningful patterns in normal data. Moreover, they often depend on handcrafted transformations tailored specific domains, hindering their generalization accross diverse problems. To address these limitations, we introduce NeuCoReClass AD, a self-supervised multi-task time series anomaly detection framework that combines contrastive, reconstruction, and classification proxy tasks. Our method employs neural transformation learning to generate augmented views that are informative, diverse, and coherent, without requiring domain-specific knowledge. We evaluate NeuCoReClass AD across a wide range of benchmarks, demonstrating that it consistently outperforms both classical baselines and most deep-learning alternatives. Furthermore, it enables the characterization of distinct anomaly profiles in a fully unsupervised manner.
Machine Learning (cs.LG)
arXiv:2508.00909 [cs.LG]
(or arXiv:2508.00909v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2508.00909 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1016/j.neunet.2026.109375 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 251 cuvinte
Subiecte conexe
CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning
arXiv · 8 iun. 2026
When Does Self-Supervised Learning Transfer to Time-Series Tasks?
arXiv · 1 oct. 2026
WinoTS: Wavelet-based Self-Distillation for Time Series Models
arXiv · 1 oct. 2026
NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection
arXiv · 12 oct. 2026