By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.
Require: Input lookback time series X ∈ RT ×N ; input Length T ; predicted length S; variates number N; token dimension D; iTransformer block number L
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.