- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
CDMD combines numerical Gaussian diffusion and categorical masked diffusion through a shared schema-aware Transformer to generate mixed-type data across heterogeneous table schemas; joint training on seven datasets demonstrates parameter savings and competitive generation quality, while pretraining on 337 datasets improves adaptation to unseen tables under limited target data and adaptation epochs.
Critical strengths
- A single shared model with approximately 10.7M parameters matches or exceeds the average quality of separately trained generators, providing convincing empirical support for cross-table parameter sharing.
- Pretraining improves generation on unseen tables under limited data and adaptation epochs, demonstrating useful transfer when target data are scarce.
Critical weaknesses
- The generalized masked diffusion largely retains SUBS’s reverse transitions and training objective, with schema-specific vocabulary restriction as the main addition, making this methodological contribution relatively incremental.
- The paper insufficiently specifies CTSyn’s two-stage training configuration and checkpoint selection, making the substantial performance gap against its closest cross-table diffusion baseline difficult to independently verify.
Questions for authors
- In the few-shot experiments, are categorical vocabularies constructed from the selected N rows or supplied by the complete schema, and do all methods receive the same categorical-domain information?
- Could the authors specify CTSyn’s training and adaptation budgets for both stages and its checkpoint-selection rules to clarify whether its substantial performance gap is affected by training configuration?
- On the same hardware, how much time do pretraining, target-table adaptation, and sampling require, and how many target tables are needed to amortize pretraining costs?
2 comments
Response to the authors
Thank you for the helpful response, which has clarified the questions raised in my review. I maintain my recommendation of weak acceptance.
Rebuttal
We thank the reviewer for their valuable feedback. In the following, we address the reviewer's questions and concerns.
For a fair comparison between baselines, we construct the categorical vocabularies from the selected N rows in the few-shot experiments. Therefore, all methods received the same categorical domain information.
For CTSyn, we used the implementation provided in their OpenReview submission [1]. While the implementation matches the description in their paper, we found discrepancies between the code and the paper in the hyperparameter settings. Therefore, we tried both settings and picked the best-performing checkpoint. For a fair comparison with our model, we trained CTSyn on the same datasets as our model in both our settings (the cross-dataset experiment and the pre-training experiment).
On the same hardware, pre-training on the 337 datasets takes 2 days, while target-table adaptation takes between 15 minutes and one hour, depending on the number of samples. Sampling a batch of 10000 rows takes less than 1 minute on average. In our experiments, training the model from scratch on the target dataset required at least 2000 epochs to converge (consistent with TabDiff), whereas a pre-trained model converged after 50 epochs.
We hope that our response clarifies the questions raised by the reviewer and are happy to clarify any further concerns!
References
[1] https://openreview.net/forum?id=Sh4FOyZRpv