- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
The authors note that the typical approaches to graph learning essentially segment the tasks of graph generation and graph comprehension by discarding the decoding head after training, then training a new decoder for classification based on the latent space embeddings. In contrast, vision and language tasts have moved toward unified models for comprehension and generation. The focus of the authors work it to evaluate the whether the seperation of graph generation and comprehension is the ``correct'' choice. To evaluate this, the authors consider a variety of different approaches to the combined comprehension/generation tasks, mimicking those which appear in the literature, while using a common architecture for the auto-encoder training and comprehension heads. These networks are applied to 5 different sets of graphs of at most 24 vertices (synthetic stochastic block model, CiteSeer, Cora, PubMed, and QM9).
Critical strengths
-
The question the authors attempt to address in interesting and important.
-
The experimental design is thorough, well thought-out, and well documented.
Critical weaknesses
-
In multiple places, the use of a non-specific referent (e.g., ``it'') compromises the clarity of the presentation to the point that several sections are incomprehensible.
-
While there are numerous experiments presented in this work, representing the authors commitment to the scientific questions, due to the space limitations the analysis and interpretation of the often reduces to highlighting single values from large tables, rather than extracting broad themes and addressing how the results answer the stated research questions.
Questions for authors
None
2 comments
Kind Follow Up
Dear Reviewer Ji4k,
With the discussion deadline approaching (November 18 AoE), we wanted to briefly follow up on our rebuttal. We revised the wording for clarity and reorganized the results around the research questions. If you have a chance to take a look, we would appreciate hearing whether these changes address your concerns. Thank you again for your time and feedback.
Rebuttal
We thank the reviewer for finding the question interesting and important and the experimental design thorough, well thought-out, and well documented. We address your concerns one by one below.
W1 (Non-specific referents such as "it"). The revision replaces each non-specific referent in the main text with the noun it refers to. Three examples follow.
W2 (Single values from large tables rather than broad themes). The revision gives the verdict of every research question in one table and moves the cell-level values to the appendix.
The results answer the research questions through four themes, which Sec. 5 discusses.
RQ5 then asks whether the generator family matters more than these interfaces. The tested prior families, a latent-diffusion prior and a VAE, shift C2ST less than prior deployment on three of five domains (Table A.22). The conclusion ends with the practical recommendations that follow from these themes.