ASTER generates pseudo-anomalies in latent space to train a Transformer anomaly classifier with LLM-enriched representations, achieving state-of-the-art results on three benchmark datasets for unsupervised time-series anomaly detection.
In: VLDB (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection
ASTER generates pseudo-anomalies in latent space to train a Transformer anomaly classifier with LLM-enriched representations, achieving state-of-the-art results on three benchmark datasets for unsupervised time-series anomaly detection.