TransDe combines HP-filter decomposition, multi-scale patch transformers, and stop-gradient KL contrastive learning to score multivariate time series anomalies, reporting top F1 on four of five public benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Decomposition-based multi-scale transformer framework for time series anomaly detection
TransDe combines HP-filter decomposition, multi-scale patch transformers, and stop-gradient KL contrastive learning to score multivariate time series anomalies, reporting top F1 on four of five public benchmarks.