- Rating
- 4
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper proposes CAMVC for incomplete and unaligned multi-view clustering. It establishes canonical coordinates using an automatically selected reference view and learns sparse soft correspondences through cluster-routed local sparse transport (CLST). Experiments cover six datasets under different missingness and unalignment settings.
Critical strengths
The paper addresses a practically relevant problem in multi-view clustering, where missing observations and unknown cross-view correspondences occur together. Learning without known sample pairs makes the setting particularly diffculty . Second, CAMVC provides a coherent framework that connects correspondence learning with sample- and view-level reliability. The integration of correspondence uncertainty into representation learning and structural integration is a meaningful aspect of the method. Experiments on six benchmarks under different missingness and unalignment settings provide encouraging evidence of the method’s effectiveness.
Critical weaknesses
The paper treats reconstruction consistency as a reliability proxy, but its interpretation in the presence of feature-dependent residual variation needs further explanation. The ablation experiments are conducted only at a 10% missingness rate, which is the easiest case. Can the performance be maintained at other missingness rates? Questions:
- How should the sample-specific reliability weights be interpreted when the observed reconstruction residual is affected by feature-dependent residual variation?
- On Synthetic3d at 50% missingness, CAMVC achieves an ACC of 0.5867. On Synthetic3d at 30% missingness, CAMVC achieves an ACC of 0.7183. With a decrease in the missingness rate, the results differ so greatly. What drives such a large improvement in performance?
- What motivates the baseline ? How does it account for an assignment that is uniform over the retained candidates?
Questions for authors
See Weakness
Response to vdwt
Thank you for your detailed review. We summarize our responses below.
Q1. Sample reliability under feature-dependent residual variation.
A: The weight qi=exp!(−2σmcc2∥R:,i∥22) controls a sample’s influence on learning; it is not a probability that its correspondence is correct. A large residual may reflect correspondence errors, feature noise, or missingness-induced representation errors. The covariance term serves a different role by modeling variation across feature directions. As shown in Eq. (21), the sample and covariance terms contribute additively to the residual update.
Nevertheless, the Euclidean definition of qi remains sensitive to feature-dependent residual variation after standardization. We will make this limitation explicit in Section 3.3 and Appendix B.2 and evaluate a covariance-normalized alternative using R:,i⊤(Σ(v))−1R:,i. This comparison will assess the sensitivity of the reliability mechanism to the residual metric.
Q2&W1. Higher-missingness ablations.
A: We agree that the component analysis should cover higher missing rates and extend the ablations to 30% and 50% missingness.
Table R1: Ablation results (%) at 30% missingness.
Table R2: Ablation results (%) at 50% missingness.
Increasing missingness from 30% to 50% reduces the available observations and cross-view overlap, leaving fewer observed constraints for correspondence estimation and representation learning. The ACC on Synthetic3d decreases from 71.83% to 58.67% under this change.
Q3. The 1/n baseline and uniform assignment over retained candidates.
A: The baseline 1/n is the maximum entry of a uniform row over all n canonical columns. Thus, the current measure quantifies concentration relative to global uniform assignment. For a row uniform over si<n retained candidates, its peak is 1/si, and the measure is positive. It therefore reflects restriction of the candidate set as well as concentration within that set.
To distinguish these effects, we will compare the original measure with a support-normalized alternative. For an observed row i, let si=nnz(Pi,:(v)) denote its support size. We define
hi=1−1/simaxjPij(v)−1/si,si>1,
with hi=1 for singleton support. Missing rows with zero support are excluded. This alternative assigns zero to rows that are uniform over supports of size greater than one. We will report its effects on fusion weights and clustering performance and clarify the distinction between global and conditional concentration in Section 3.5 and Appendix B.6.