DJEnsemble: On the Selection of a Disjoint Ensemble of Deep Learning Black-Box Spatio-Temporal Models
This work addresses the optimization of model allocation for spatio-temporal predictions, which is incremental as it builds on existing ensemble methods with a novel cost-based approach.
The paper tackles the problem of selecting and allocating a disjoint ensemble of black-box spatio-temporal models to answer predictive queries, achieving up to 4X improvement in execution time and almost 9X improvement in prediction accuracy compared to traditional ensemble approaches.
In this paper, we present a cost-based approach for the automatic selection and allocation of a disjoint ensemble of black-box predictors to answer predictive spatio-temporal queries. Our approach is divided into two parts -- offline and online. During the offline part, we preprocess the predictive domain data -- transforming it into a regular grid -- and the black-box models -- computing their spatio-temporal learning function. In the online part, we compute a DJEnsemble plan which minimizes a multivariate cost function based on estimates for the prediction error and the execution cost -- producing a model spatial allocation matrix -- and run the optimal ensemble plan. We conduct a set of extensive experiments that evaluate the DJEnsemble approach and highlight its efficiency. We show that our cost model produces plans with performance close to the actual best plan. When compared against the traditional ensemble approach, DJEnsemble achieves up to $4X$ improvement in execution time and almost $9X$ improvement in prediction accuracy. To the best of our knowledge, this is the first work to solve the problem of optimizing the allocation of black-box models to answer predictive spatio-temporal queries.