Self-pretraining on the target dataset yields 0.7 to 9.9 percentage point accuracy gains over from-scratch transformers across three medical time-series tasks, though the experimental design does not control for total training epochs.
Self-supervised learning for time series analysis: Taxonomy, progress, and prospects,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
Self-pretraining on the target dataset yields 0.7 to 9.9 percentage point accuracy gains over from-scratch transformers across three medical time-series tasks, though the experimental design does not control for total training epochs.