This PR is to add Time Series Saliency (TSSaliency) Explainer algorithm for forecasting, time series classification and regression use cases.
Short description of the algorithm is: Time Series Saliency (TSSaliency) Explainer is a model agnostic saliency explainer for time series associate tasks. The saliency supports univariate and multivariate use cases. It explains temporal importance of different variates on the model prediction. TSSaliency incorporates an integrated gradient method for saliency estimation. The saliency measure involves the notion of a base value. For example, the base value can be the constant signal with average value. The saliency measure is computed by integrating the model sensitivity over a trajectory from the base value to the time series signal. The TSSaliency explainer provides variate wise contributions to model prediction at a temporal resolution.
This PR is to add Time Series Saliency (TSSaliency) Explainer algorithm for forecasting, time series classification and regression use cases.
Short description of the algorithm is: Time Series Saliency (TSSaliency) Explainer is a model agnostic saliency explainer for time series associate tasks. The saliency supports univariate and multivariate use cases. It explains temporal importance of different variates on the model prediction. TSSaliency incorporates an integrated gradient method for saliency estimation. The saliency measure involves the notion of a base value. For example, the base value can be the constant signal with average value. The saliency measure is computed by integrating the model sensitivity over a trajectory from the base value to the time series signal. The TSSaliency explainer provides variate wise contributions to model prediction at a temporal resolution.
Required Dependencies:
numpy
pandas <= 1.4.3
[x] algorithm folder is added here
[x] example notebooks are added here
[x] updated the examples readme here with univariate time series classification and multivariate forecasting notebook details.
[x] example time series model wrappers are added here. These can be customized or extended further.
[x] This explainer requires default dependencies only. So, included it in TSICE job here.