Review for NeurIPS paper: Coherent Hierarchical Multi-Label Classification Networks

The submission introduces a new loss function for hierarchical multi-label classification. The justification of the loss function is purely empirical given in a form of results obtained on an illustrative synthetic example. The learning under this loss can be efficiently performed using GPUs. The introduced algorithm obtains the state-of-the-art results. The reviewers agreed that the paper is clearly written, the loss function well-motivated and interesting, and the results worth publishing.