MFF-FTNet combines CoST-style contrastive learning, TimesNet-style top-k frequency selection, and TCN-style multi-scale convolutions, reporting modest average MSE gains but leaving the forecasting loss undefined.
Time series prediction using deep learning methods in healthcare,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MFF-FTNet: Multi-scale Feature Fusion across Frequency and Temporal Domains for Time Series Forecasting
MFF-FTNet combines CoST-style contrastive learning, TimesNet-style top-k frequency selection, and TCN-style multi-scale convolutions, reporting modest average MSE gains but leaving the forecasting loss undefined.