Review for NeurIPS paper: Feature Importance Ranking for Deep Learning

Strengths: Post rebuttal Connection to the papers I recommended has been made clear (instance-wise versus population-wise) as is also the case for the suggestions made by R3. The authors have provided detailed contextualisation and agreed to add it to the paper. In terms of performance comparison, they have added another experiment to their evaluation with a much larger set of features, to demonstrate the scalability to large-sized datasets. From the experiments in the paper, and given the new addition, it becomes clear that their method is able to yield higher performance via the selection of smaller number of features. The computational cost is indeed high, given the alternate training routine involving two full-size DNNs, which going forward could be an interesting area to work in i.e. downscaling of these units.