SPAT, a sensitivity-based method that prunes whole attention modules using a dispersion score called SEND, cuts FLOPs by roughly 35% on average while slightly improving MSE/MAE on several forecasting benchmarks.
Title resolution pending
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
-
SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models
SPAT, a sensitivity-based method that prunes whole attention modules using a dispersion score called SEND, cuts FLOPs by roughly 35% on average while slightly improving MSE/MAE on several forecasting benchmarks.