- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes an alternative way of computing a drifting field for drifting models. The performance of the methods is tested on MNIST and CIFAR-10 datasets.
Critical strengths
None
Critical weaknesses
Novelty and presentation My major concern is that it is difficult to understand what exactly the paper proposes. Equations 11–13 suggest that the main difference compared to Deng et al. (2026) is an alternative way of estimating the vector field , which is given in Equations 12–13. It is not clear how this estimator relates to clustering. Moreover, Deng et al. (2026) mention that is necessary as it improves the performance of the algorithm. The question is discussed briefly in lines 221–223, as well as in footnote 4. However, I find the discussion insufficient. Besides, the claim "... MSE loss both is much quicker and works well regardless on real, high-dimensional data" is not fully supported by the experimental results, which I talk about below. Finally, I find the theoretical justification presented in Section 3 difficult to follow. I detail my questions about the exposition of the theory in Inconsistencies.
Experiments I have the following concerns about the experiments in the paper:
- No comparisons with baselines, such as Deng et al. (2026), Gretton et al. (2026), and Han et al. (2026).
- Figure 3, which supposedly motivates the proposed algorithm, is a little questionable. Drifting models are capable of learning such a distribution if the temperature is tuned. It should be noted that the proposed algorithm also has as a hyperparameter that possibly requires tuning.
- The FID scores on CIFAR-10 are high, which suggests that the algorithm hasn't fully converged or requires substantial improvements.
- It has been shown (Deng et al., 2026; Han et al., 2026) that drifting models can be successfully scaled to high-resolution images. The question remains whether the proposed method can achieve the same results.
Inconsistencies
- Line 86 and Equation 1: is used, but is never defined;
- The term "positive normalised kernel" in line 84 is not defined. I suspect it should have been "positive definite".
- Equation 11 and Equation 5 define optimisation objectives, yet it is unclear with respect to which variables these objectives are defined.
- It is not clear why is a valid density. Moreover, it is not clear how depends on .
Questions for authors
Clarifications Please clarify what the main advantages of the proposed way of computing the drifting field are, as opposed to Deng et al. (2026) and Han et al. (2026). I venture to suggest presenting your method as an algorithm similar to Algorithm 2 in Deng et al. (2026) or Algorithm 1 in Han et al. (2026).
Suggestions
- For the low-dimensional experiments, I suggest comparing your method against the baselines discussed in Gretton et al. (2026).
- For experiments on images, I suggest comparing your method against Deng et al. (2026) and Han et al. (2026). I appreciated the attempts to do so in Tables 4 and 5; however, I believe the results can be substantially improved on both CIFAR-10 and MNIST.
Response to reviewer mRMs
We thank the author for reading our paper and their questions and constructive criticisms. Though we will be withdrawing this submission we would nevertheless like to address their questions below.
Weaknesses:
My major concern is that it is difficult to understand what exactly the paper proposes. Equations 11–13 suggest that the main difference compared to Deng et al. (2026) is an alternative way of estimating the vector field , which is given in Equations 12–13. It is not clear how this estimator relates to clustering.
We agree that the connection between the clustering loss and the MSE proxy loss was not fully emphasised and made clear. Appendix B has now been added with a step-by-step derivation of the two losses, showing that they are equivalent up to a weighting by total responsibility per centroid point, and have equal zeroes in terms of the generated points xi.
Figure 3, which supposedly motivates the proposed algorithm, is a little questionable. Drifting models are capable of learning such a distribution if the temperature is tuned. It should be noted that the proposed algorithm also has τ as a hyperparameter that possibly requires tuning. We thank the reviewer for bringing this to our attention, and work is ongoing on tuning our ordinary drifting approach. In our proposed algorithm, τ needs only to anneal from a high value to a low value - we never tune it instantaneously. The shape of the anneal is simple and exponential, as discussed and illustrated on page 18 in Appendix E.
Clarifications:
Please clarify what the main advantages of the proposed way of computing the drifting field are, as opposed to Deng et al. (2026) and Han et al. (2026). I venture to suggest presenting your method as an algorithm similar to Algorithm 2 in Deng et al. (2026) or Algorithm 1 in Han et al. (2026).
The proposed way of computing the drifting field, while similar to Algorithm 2 in Deng et al. (2026), differs in several key respects.
Algorithm 2 in Deng et al. takes a geometric mean of two softmaxes of the kernel |x_i-y_j|/\tau, one softmax over i (the generated points) and the other over j (the data points). This is an effective but unexplained method to prevent collapse during learning. Our method is equivalent to a single softmax of the kernel over generated points for each data point. There is no row normalisation. Algorithm 2 in Deng et al. is not an exact gradient of a potential, whereas ours is the gradient of a free energy defined from classical clustering theory. Algorithm 2 in Deng et al., along with all related drifting algorithms, makes use of a repulsive term to ensure coverage of the data and sample diversity. For us, generated points compete to describe the data under a clustering objective, and spread out as a result of this competition.
For the low-dimensional experiments, I suggest comparing your method against the baselines discussed in Gretton et al. (2026). The low-dimensional datasets in Gretton et al. (2026) are not fully defined in the paper, but can be inferred from the visual results. Our method was tested against Deng’s drifting algorithm on a selection of similar targets, and the results may be seen in Appendix F. Both methods achieve excellent, comparable performance on these simple targets.