positive comment
We thank all reviewers for their positive comments on idea novelty, technical quality, paper writing, and promising
Please kindly refer to our response to Q1 of R#2, which will be added in our paper.
We thank all reviewers for their positive comments on idea novelty, technical quality, paper writing, and promising
Please kindly refer to our response to Q1 of R#2, which will be added in our paper.
experiment results on Neural GTD, (b) an expanded discussion on the theoretical results and relation to prior works
We will include your references in the final version.
To Reviewer # 1: Thanks for your positive comments on our paper!
Q1: Why is Full-Batch outperformed by LADIES? It is true that LADIES is designed as an approximation of original GCN. The reason is: real graphs are often noisy and incomplete. Figure 1: Experiments on the PubMed dataset, which contains 19717 nodes and 44338 edges. Q1: "Similar names generate several misunderstandings and confusions" We apologize the title causes confusing.
We would like to thank the reviewers for their helpful feedback, and for their positive comments regarding the originality
We will clarify this formulation in the paper. Conjugate MDPs are an interesting framework for learning useful abstractions. Thank you for your feedback - we will improve the legibility of all figures with attention to B&W . "Ours" in Figure 2 is indeed using We are indeed using the best τ found for GAE when running with λ = 0 . We will clarify this also.