- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper presents a unified framework for distributional training of one-step visual generators, separating distribution modeling from the discrepancy used for matching. Within this framework, the authors propose MGFlow, which models feature distributions using Gaussian mixtures and combines mass-constrained sample allocation with paired component updates. Both optimal-transport-based and KL-based variants are developed. Experiments on ImageNet across multiple generator backbones and text-to-image generation demonstrate the effectiveness of the approach, with additional evaluations using held-out feature encoders.
Critical strengths
-
A useful conceptual framework supported by a coherent algorithmic design. Separating distribution modeling from matching discrepancy clarifies the relationships between existing approaches and provides a systematic way to develop alternatives. MGFlow makes this framework concrete: mass-constrained allocation enforces reference component proportions in the assigned samples, while paired updates preserve the correspondence between allocation and transport. The ablations support the importance of combining these two mechanisms.
-
Substantial empirical validation beyond the conceptual formulation. The ImageNet experiments cover multiple backbones and model sizes, and improvements on held-out feature encoders provide evidence that the benefits extend beyond the representations used for training. The appendix also includes detailed implementation, ablation, and computational analyses. Together, these results strengthen the case that the proposed framework leads to a useful training method.
Critical weaknesses
-
The image-level evidence for improved mode coverage remains indirect. The toy experiment and assignment ablations support the proposed mechanism, but aggregate distributional scores do not distinguish better mode proportions from better within-mode fidelity. Since correcting mass imbalance is central to the motivation, a direct coverage diagnostic on generated images would strengthen the empirical justification.
-
Increasing the number of mixture components is not straightforward. Appendix I.2 shows that some components receive too few samples to reliably estimate their full covariances, while longer EMA windows slow adaptation to the changing generator. This limits the granularity of the mixture representation and leaves its scalability to distributions requiring many more components uncertain.
Questions for authors
-
Clarification of the theoretical scope: Appendix B.5 appropriately distinguishes continuous-flow energy descent from a finite-step guarantee for generator optimization. For practical MGFlow-KL, does any descent interpretation also survive the combination of LP reassignment, EMA statistics, and covariance regularization? If not, could the authors make this boundary more explicit in the main text?
-
Evidence supporting the proposed mechanism: Can the authors provide a direct diagnostic on generated images comparing mode proportions or coverage under posterior assignment, LP allocation with global updates, and LP allocation with paired updates? This would help determine whether the improvements specifically reflect better mass allocation, rather than primarily better within-mode fidelity.
3 comments
Follow-up on our rebuttal
Dear Reviewer yN9U,
Thank you again for your thoughtful comments. Your questions prompted us to measure component coverage directly and make the descent argument more explicit. The rebuttal reports component shares across all 16 components, discusses the sample requirements as the number of components grows, and explains the local descent interpretation under fixed LP assignments.
If the response addresses your concerns, we would be grateful if you would consider raising your score. We would be happy to elaborate on any point that would benefit from further discussion.
Thank you for the detailed rebuttal and follow-up clarification. I appreciate the authors' efforts to address my concerns. Overall, the explanation has addressed my most questions regarding component coverage and the theoretical scope of the descent argument. Considering the paper’s overall insights and novelty, I remain inclined to maintain my original rating of weak accept
Response to Reviewer yN9U
Thank you for recognizing the value of our unified framework, the coupled allocation-and-update design, and the breadth of the empirical validation. We address the requested coverage diagnostic and clarify the statistical and theoretical scope below.
[W1, Q2] A direct diagnostic of generated images under different assignments
The assignment ablation in Table 2 reports generation quality across the three variants. As a generation metric, Fréchet Distance is itself sensitive to mode coverage, not only in-mode fidelity, and thus lower FD already reflect better mass allocation. To further test mass allocation directly, we add a complementary component-share diagnostic with JiT-B trained on SIM encoder spaces. LP-paired most closely matches the full 16-component share vector: it has the lowest TV and the smallest absolute share error on 15 of the 16 components at the reported precision.
We compare Posterior, LP-global, and LP-paired using K=16, the same initialization, and 10 training epochs. Our reference Inception Gaussian mixture evaluates 50,000 newly generated one-step images and 50,000 real images. Each component's soft share is the average posterior probability. Crucially, evaluation imposes no LP quotas: it measures where generated images actually fall under the reference GMM.
We sort the components once by decreasing real-data share and show ranks 1, 4, 8, 12, and 16, spanning the largest to the smallest components. Every method is evaluated against the same component identities. Values are percentages.
Across all 16 components, the Total Variation Distance (TV) is 0.21682 for Posterior, 0.94625 for LP-global, and 0.03782 for LP-paired. The maximum absolute component-share deviation is approximately 1.28 percentage points for LP-paired, compared with 9.77 for Posterior and 94.63 for LP-global. This shows why training-time quotas alone are insufficient and why preserving the allocation in paired update matters.
[W2] Statistical support when increasing the mixture component count
We thank the reviewer for raising this point. We would like to clarify that this limitation primarily stems from the scale of ImageNet, where increasing the number of mixture components reduces the samples available for reliable covariance estimation, rather than from MGFlow itself. In fact, this valuable comment highlights an exciting direction for future research on finer-grained mixture representations using substantially larger, industry-scale datasets. We will discuss this promising direction in the appendix.
[Q1] Descent under LP reassignment, EMA, and covariance regularization
A local descent interpretation survives LP assignment and covariance regularization; EMA makes the current-moment identity approximate while providing a more stable population estimate. For each global batch and encoder/branch, Algorithm 3 solves the LP once and keeps the assignment fixed throughout that update. We then fix the assignment matrix R and define the paired KL using the current R-weighted means and covariances of the generated features Z, with λI added to both reference and generated covariances:
FRλ=∑kπkKL(N(μk(Z),Σk(Z)+λI)∥N(μp,k,Σp,k+λI))
Direct differentiation gives:
∇zFRλ=−vpair,n/B
This identity holds for any fixed assignment satisfying the mass constraints, including LP assignments; it does not require differentiating through the assignment solver. Covariance regularization changes the objective to the KL between regularized Gaussians while preserving this gradient relationship. Combining this identity with Eq. (46), the detached-target regression gradient equals η times the objective’s parameter gradient at the current iterate. A sufficiently small gradient-descent step therefore decreases this fixed-assignment objective under standard smoothness conditions.
EMA introduces a deliberate trade-off between tracking the current distribution and reducing minibatch noise in its moment estimates. By aggregating statistics across batches, it provides a larger effective sample population without requiring a correspondingly large gradient batch. This strategy has empirical support in FD-Loss Sec 4.1, where the EMA estimator performs well across a broad range of decay rates and its best setting outperforms the tested queue-based alternatives.
We will add the explicit claims to Appendix B.5 regarding assignment algorithms and covariance regularization, and clarify the theoretical boundary of EMA updates in the main text.