WinTSR multiplies feature ablation scores by a time relevance score obtained by masking all features at each lag, improving faithfulness metrics across five models and three datasets.
(2020) ablated the input features by sampling counterfactuals from the bootstrapped distribution
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
-
WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models
WinTSR multiplies feature ablation scores by a time relevance score obtained by masking all features at each lag, improving faithfulness metrics across five models and three datasets.