Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned representations.
Self-supervised learning for time series analysis: Taxonomy, progress, and prospects.IEEE Transactions on Pattern Analysis and Machine Intelligence, 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
-
Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models
Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned representations.