Metraipolis › archive › dc_76ba3fd5f205

LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection — arXiv:2609.38789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38789
License (as archived)
CC0-1.0
Archived
2026-10-07T13:45:33.127Z
SHA-256 of the archived text
5deedadf04f1cf3b238f5ee3cb65ae9db14e24456b16f04f69b2e356029bf88d
Stable URL of this page
https://metraipolis.com/documento/dc_76ba3fd5f205

How to cite

LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection — arXiv:2609.38789 — arXiv (en), https://arxiv.org/abs/2609.38789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76ba3fd5f205 (Metraipolis archive dc_76ba3fd5f205, sha256 5deedadf04f1cf3b238f5ee3cb65ae9db14e24456b16f04f69b2e356029bf88d)
BibTeX
@misc{dc76ba3fd5f205,
  title = {LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection — arXiv:2609.38789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76ba3fd5f205; sha256 5deedadf04f1cf3b238f5ee3cb65ae9db14e24456b16f04f69b2e356029bf88d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 consistently and is not provided by standard multivariate time-series anomaly detection benchmarks. This setting poses two challenges: (1) conditioning masked reconstruction on window-specific semantics without exposing exact numerical targets or anomaly-specific cues, and (2) using a window-independent concept of normality as a complementary semantic reference rather than an independent anomaly detector. We propose LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Time Series (LEARN-TS), which uses a frozen language model to construct two role-separated semantic representations without requiring temporally paired external text. Window-specific observation semantics encode temporal and cross-variable context without exact numerical values to guide channel-shared patch-masked reconstruction. A fixed, dataset-agnostic normality prompt provides a window-independent semantic reference for aligning normal representations and estimating normality discrepancy. At inference, masking each temporal patch once yields timestamp-level reconstruction evidence, conditionally modulated by discrepancy from a separate unmasked view. Across four benchmarks, LEARN-TS achieves the highest mean performance in 13 of 16 dataset-metric comparisons. Controlled ablations examine observation conditioning, joint normality alignment and scoring, and reference content, showing dataset-dependent ranking benefits and modest average gains from semantic over random references.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38789 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T13:18:10.262Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).