- Rating
- 3
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces D-ViCe, a method for CAD model retrieval and graph representation learning. It employs two target networks to promote consistency between representations of different views of the same sample. Experiments demonstrate substantial performance improvements on the SolidLetters retrieval task, as well as gains when the method is integrated into existing graph contrastive learning methods.
Critical strengths
- The method achieves substantial performance improvements on the main retrieval tasks.
- Combining a fixed target network with a target network that is updated during training yields additional performance gains, which is an interesting finding.
Critical weaknesses
None.
Questions for authors
- Regarding adaptive temperature adjustment during training, the temperature reaches its lower bound within the first 45 training steps and remains essentially constant thereafter. Could the temperature simply be fixed at this lower bound from the outset?
- Tables 3–5 in the main text report R@5, whereas Tables 8–10 in the appendix report R@10. However, the value 0.9496 repeatedly appears as the default result in both. Is this merely a numerical coincidence?
We thank the reviewer for the positive assessment and for the two precise questions, which helped us clarify the paper. We answer them below.
Note on the metric. While preparing the rebuttal, we found that the metric reported as R@5 counts a hit within the ten nearest neighbors. We have relabeled it as R@10 throughout; this changes only the label (see Q2).
Q1. Could the temperature simply be fixed at its lower bound from the outset?
We tested this directly. Training the full model with the controller disabled and τ fixed at τmin=0.05 from the first step reaches R@10 = 0.9269±0.001 over three seeds, compared with 0.9497±0.0005 for D-ViCe, a drop of 2.28 points. Although the temperature is constant after about 45 steps, this early phase matters: starting directly at a sharp temperature from random initialization hurts training, while the controller reaches it gradually. The controller's path is practically a short schedule from 0.1 to 0.05, which it obtains without tuning the schedule length. We add this comparison to Table 3 and state this interpretation in Section 2.2.
Q2. Is the repeated value 0.9496 a numerical coincidence?
No, and we thank the reviewer for spotting this. All these tables report the same metric for the same default configuration. While checking the evaluation code, we found that the metric labeled R@5 in Tables 3–5 counts a hit within the ten nearest neighbors, i.e. it is R@10, as correctly labeled in Tables 8–10. We have relabeled the metric as R@10 throughout the paper; all values are unchanged. The default configuration is now reported as 0.9497±0.0005, the mean over three seeds.
We are grateful for the reviewer's positive evaluation and careful reading, which helped us correct the metric label and strengthen the analysis of the temperature controller. If any further clarification or experiment would help, we would be glad to provide it. We hope these answers reinforce the reviewer's assessment, and we would sincerely appreciate it if the reviewer would consider raising the score.