WassersteinGrad aggregates perturbed gradient attribution maps via their entropic Wasserstein barycenter to avoid blurring from geometric shifts in explanations of autoregressive weather forecasts.
Local explanation methods for deep neural networks lack sensitivity to parameter values
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
WassersteinGrad aggregates perturbed gradient attribution maps via their entropic Wasserstein barycenter to avoid blurring from geometric shifts in explanations of autoregressive weather forecasts.