The paper proposes a hierarchical model for multivariate point process data with known network information. It uses a mixture of Hawkes processes for the point process observations, and the treats the observed network as a mixed membership stochastic block model sharing the same mixture weights. The main technical novelty is to use model agnostic meta-learning (MAML) to implement the hierarchical prior on the Hawkes process parameters. However, this technical contribution (MAML + Hawkes/network models) is not compared to standard hierarchical Bayesian techniques. Specifically, the parameters \theta_{k}^{(i)} are only three dimensional (background rate \mu, scale \delta, and time constant \omega). The authors should show that MAML is really necessary here; specifically, that textbook hierarchical modeling techniques [like a simple conditional distribution p(\theta^{(i)} | \theta)] do not suffice. R2 briefly commented on this in their review as well. Though the general idea of hierarchical modeling of Hawkes processes and networks is interesting and the submitted paper develops some novel methods for this problem, the omission of standard hierarchical modeling baselines is a critical shortcoming. Despite these serious concerns, the reviewers gave favorable enough scores to warrant acceptance. I would still strongly advise the authors to implement a simple hierarchical modeling baseline before final publication. Other issues: - The latent variable z_i is never actually defined and does not appear in Fig 1, though the reader has to guess that it is an class indicator for \tau_i.