Randomly dropping 60% of patches before masked pre-training improves PatchTST time-series forecasting accuracy and training speed, though the paper's theoretical explanation is not sound.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Enhancing Masked Time-Series Modeling via Dropping Patches
Randomly dropping 60% of patches before masked pre-training improves PatchTST time-series forecasting accuracy and training speed, though the paper's theoretical explanation is not sound.