PLanTS combines FFT-driven multi-granularity patching, MXCorr-based soft contrastive loss, and next-transition prediction, claiming state-of-the-art SSL results on UEA, PTB-XL, ETT, and Yahoo benchmarks.
Dtw-d: time series semi-supervised learning from a single example
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
PLanTS: Periodicity-aware Latent-state Representation Learning for Multivariate Time Series
PLanTS combines FFT-driven multi-granularity patching, MXCorr-based soft contrastive loss, and next-transition prediction, claiming state-of-the-art SSL results on UEA, PTB-XL, ETT, and Yahoo benchmarks.