Cost-Aware Counterfactuals for Black Box Explanations
Natalia Martinez Gil, Kanthi Sarpatwar, et al.
NeurIPS 2023
Data privacy and explainability are two important requirements for any mature AI enabled system. Local explainability for a prediction or forecast amounts to assigning credit or blame to different input features of a model responsible for that prediction. Aggregation of these predictions and explanations to higher levels of hierarchy is often met with the challenge of privacy loss as it reveals characteristics of individual data points to a wider audience. Hence, an optimal tradeoff between privacy and explainability is explored in the context of hierarchical time series forecasting.
Natalia Martinez Gil, Kanthi Sarpatwar, et al.
NeurIPS 2023
Pavithra Harsha, Ali Koc, et al.
INFORMS 2021
Daniel Karl I. Weidele, Hendrik Strobelt, et al.
SysML 2019
Michael Hersche, Francesco Di Stefano, et al.
NeurIPS 2023