Review for NeurIPS paper: Detecting Interactions from Neural Networks via Topological Analysis

All knowledgeable referees have confirmed the novelty parts and contributions of this work. I recommend acceptance of this paper and suggest the authors refine the paper before publication. Particularly, the concerns and suggestions raised by R#4 & R#3 should be addressed. AC and SAC discussed this paper on the issues raised by R3 and converged to accept. The authors are encouraged to discuss whether CNN belongs to the models that can be explained by the method proposed.