AiT forecasts irregular multivariate time series by using time-point-dependent attention weights in place of static linear layers, reporting improved accuracy and runtime on four benchmarks.
Neural flows: Efficient alternative to neural odes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting
AiT forecasts irregular multivariate time series by using time-point-dependent attention weights in place of static linear layers, reporting improved accuracy and runtime on four benchmarks.