- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses the incomplete multimodal learning problem and proposes TWIN, a two-stage Mixture-of-Experts (MoE) imputation framework. The authors interpret the sparse MoE routing mechanism as a Voronoi geometric partition of the feature space, and theoretically prove that intra-expert imputation has a tighter worst-case error bound than unconstrained global inter-expert imputation.
Critical strengths
- The attempt to interpret the semantic locality of MoE routing from a geometric perspective provides intuitive inspiration for missing modality imputation, and the idea is internally consistent to some extent.
- The two-stage imputation design has clear logic. The combination of distribution constraint and local aggregation is engineering-wise easy to implement and requires only minor modifications to the MoE backbone.
Critical weaknesses
- The theoretical contribution is contrived, severely disconnected from the actual method, and has extremely limited applicability. The conclusion in Proposition 1 that sparse routing is equivalent to Voronoi space partitioning strictly relies on a very specific routing bias setting. Standard sparse MoE uses learnable routing biases end-to-end instead of this fixed form. The paper only vaguely mentions dynamically computing to achieve Voronoi routing, but fails to explain how this modification affects the representational capacity of MoE itself, nor does it verify whether the Voronoi geometric assumption still holds under standard learnable routing.
- The extension to Soft MoE completely lacks theoretical support. Soft MoE adopts an expert-choice token routing paradigm and does not have discrete Voronoi cell structures. The migration of the locality principle has no geometric basis and is only empirically tested through simple experiments, resulting in severely insufficient theoretical rigor.
- Experimental comparisons are severely incomplete, baseline selection is outdated, and core conclusions are unconvincing. Comparisons with current mainstream technical lines are entirely missing. The paper does not include any generative multimodal completion methods based on diffusion models or flow matching, nor does it compare with recent self-supervised missing modality learning methods based on masked modeling. Against the background that generative completion has become a core track in incomplete multimodal learning, only comparing MoE-based methods from 2021–2025 and early traditional methods completely fails to support the claim of state-of-the-art.
- The evaluation dimension is single, and the fairness of comparison is questionable. The paper only evaluates imputation quality by downstream classification metrics, without setting reconstruction metrics (such as MSE, cosine similarity) to directly measure imputation accuracy, making it impossible to conduct horizontal comparison with generative methods focusing on signal reconstruction.
Questions for authors
Please see Weaknesses.
Dear Reviewer,
As the end of rebuttal is approaching, we kindly request you to engage with us for further discussion and we are open and happy to address any concern you have.
Kind regards