A sparse-attention transformer that picks the top past time steps and masks variables one at a time outperforms a fixed-lag VAR baseline for Granger causal discovery on synthetic linear time series.
Title resolution pending
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
-
Transformers with Sparse Attention for Granger Causality
A sparse-attention transformer that picks the top past time steps and masks variables one at a time outperforms a fixed-lag VAR baseline for Granger causal discovery on synthetic linear time series.