FEI is a non-contrastive self-supervised method for time series that uses frequency masking prompts to infer embeddings, and it outperforms contrastive baselines in transfer tests.
A.; Keogh, E.; Kamgar, K.; Yeh, C.-C
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
-
Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
FEI is a non-contrastive self-supervised method for time series that uses frequency masking prompts to infer embeddings, and it outperforms contrastive baselines in transfer tests.