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.

The paper proposes a relevant and novel idea and the experiments are comprehensive. The technical contribution is strong. The paper is well written and clear. After the author response, where an important missing comparison to the state of the art was provided, all reviewers agree on accept.

Deep metric learning plays a key role in various machine learning tasks. Most of the previous works have been confined to sampling from a mini-batch, which cannot precisely characterize the global geometry of the embedding space. Although researchers have developed proxy- and classification-based methods to tackle the sampling issue, those methods inevitably incur a redundant computational cost. In this paper, we propose a novel Proxy-based deep Graph Metric Learning (ProxyGML) approach from the perspective of graph classification, which uses fewer proxies yet achieves better comprehensive performance. Specifically, multiple global proxies are leveraged to collectively approximate the original data points for each class.