PFML predicts statistical functionals of masked time-series frames from unmasked context, yielding non-collapsed representations and performance on par with data2vec across IMU, speech, and EEG tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse
PFML predicts statistical functionals of masked time-series frames from unmasked context, yielding non-collapsed representations and performance on par with data2vec across IMU, speech, and EEG tasks.