Review for NeurIPS paper: Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

Weaknesses: I am a bit concerned about some of the claims in the paper being too strong. For example, the authors state at L67 that, "To our best knowledge, this is the first work that introduce graph classification into DML." However, I would be very careful making claims like this. There are many approaches in metric learning now that do similar things. This approach is quite similar to yours actually. They use graphs as well as label propagation for deep metric learning, somewhat along the lines of what you do.