Across ten public datasets, a reconstruction-based inverted transformer with per-variate anomaly labelling achieves the best or tied best MCC on most datasets, but the comparison is weakened by test-set-based configuration selection.
Aggarwal, and Jiawei Han
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series
Across ten public datasets, a reconstruction-based inverted transformer with per-variate anomaly labelling achieves the best or tied best MCC on most datasets, but the comparison is weakened by test-set-based configuration selection.