- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This article proposes a Prior-Corrected Anchor Learning method, termed PCAL, which jointly learns view-specific anchor matrices, a shared anchor representation, and discrete clustering assignments within a unified framework. PCAL reconstructs each view through the shared anchor representation and aligns the anchor matrix of each view with the shared semantic prior via orthogonal projection. Building upon this mechanism, this work further introduces regularized view-specific correction matrices, enabling the shared prior to adapt to the feature discrepancies across different views. In addition, a discrete factorization term is incorporated to directly connect anchor representation learning with cluster label assignment, thereby avoiding additional spectral clustering post-processing.
Critical strengths
-
This article proposes a Prior-Corrected Anchor Learning method and further introduces regularized view-specific correction matrices, enabling the shared prior to adapt to the feature discrepancies across different views.
-
A discrete factorization term is incorporated to directly connect anchor representation learning with cluster label assignment, thereby avoiding additional spectral clustering post-processing.
Critical weaknesses
-
The novelty of the proposed PCAL is not very clear in Figure 1 and the new parts in this figure can be highlighted. The collections among the part view-specific prior correction, shared anchor representation and discrete cluster assignment should be given in this description for Figure 1.
-
The authors give the compact view-specific prior correction in 3.2 for prior-corrected anchor learning. PCAL uses a predefined category-anchor grouping matrix Y as a common reference. Constructing this matrix does not require ground-truth sample labels. The mentioned compact view-specific prior correction is not clearly presented for this part, especially how compact can be explained.
Questions for authors
-
The shared anchor representation is the popular-used words for the existing multi-view clustering works for large-scale data. Therefore, using shared anchor representation is not very reasonable as the title of this part and the authors should use some representative words in summarizing this part.
-
The authors do not give enough explanations or analysis for running time and scalability in 5.3 for the experiment. As is known, the efficiency is an important metric for multi-view clustering for large scale as well as effectiveness. Then further analysis for running time and scalability is expected to be given in this part.
-
The authors can give the shortcomings of this work and further study can be presented in Conclusion part. The authors just give that future work will investigate which forms of view heterogeneity benefit most from prior correction and assess computational efficiency under more closely matched preprocessing and parameter-search protocols. How this mentioned future work relates with the proposed work in this paper?
5 comments
Q3: The shared anchor representation is the popular-used words for the existing multi-view clustering works for large-scale data. Therefore, using shared anchor representation is not very reasonable as the title of this part and the authors should use some representative words in summarizing this part.
A3: Good question! The current title Shared Anchor Representation names the variable , a concept widely used in anchor-based multi-view clustering. A more informative title would describe what Section 3.1 formulates. In Eq. 1, each view is reconstructed as . The anchor matrix accounts for the feature space of view , while the shared coefficient matrix gives each sample a common representation across views. We propose replacing the heading 3.1 Shared Anchor Representation on page 3, line 158 of the submitted manuscript with the following title. 3.1 Multi-View Reconstruction with Shared Anchor Coefficients
Q4: The authors do not give enough explanations or analysis for running time and scalability in 5.3 for the experiment. As is known, the efficiency is an important metric for multi-view clustering for large scale as well as effectiveness. Then further analysis for running time and scalability is expected to be given in this part.
A4: Thanks! PCAL scales with the number of samples by keeping its main linear systems in the -dimensional anchor space. As samples are added, the shared representation and the assignment matrix gain one column per sample. The coefficient matrices in Eqs.5 and 8 remain , and the representation update reuses a single factorization for all right-hand sides. The view-specific correction matrices require$Vkm$ entries, independent of for fixed , , and . This structure yields two scaling properties. First, Eq.15 gives a per-iteration cost that grows linearly with when the anchor count, cluster count, feature dimensions, and number of views are fixed. Total optimization time also depends on the iteration count. Second, the principal storage bound in Eq. 16 is$\mathcal{O}(mn+Dm+Vkm+m^2)$ , where is the sum of the feature dimensions across views. This bound excludes input data and temporary buffers. For example, in the NUSWIDEOBJ experiment, increasing the sample count from 6,002 to 30,000 increases the number of entries in from 186,062 to 930,000, while both main coefficient matrices remain$31\times 31$ . To test this behavior in practice, we varied the sample count on cluster-stratified subsets of NUSWIDEOBJ while keeping the model parameters fixed. Each subset size was run three times with seeds 11–13. The solver timings include initialization and optimization and end before final label-index extraction.
| Number of samples | PCAL solver time (s) |
|---|---|
| 6,002 | |
| 12,001 | |
| 17,999 | |
| 23,998 | |
| 30,000 |
All five sample sizes were processed with the same model settings. The experiment measures elapsed time through 30,000 samples, while Eq. 16 describes how the sizes of the stored matrices grow. In the separate cross-method comparison that times methods through final label output, PCAL takes 20.408s on the full dataset. This is faster than SMVSC (50.468s), FPMVS-CAG (98.619s), and OMSC (105.523s), which achieve higher ACC. FastMICE is faster (16.383s) and achieves higher NMI, while PCAL achieves higher ACC . We propose replacing lines 416–431 on page 8 of the submitted manuscript, from On CCV, it achieves through the end of Section 5.3, with the following text. On CCV, PCAL achieves the highest mean ACC and NMI in 0.631s. On NUSWIDEOBJ, it produces labels for 30,000 samples in 20.408s on average. As the sample count increases, and gain one column per sample, while the main coefficient matrices remain and the prior corrections retain entries. With the model dimensions fixed, both per-iteration computation and principal storage grow linearly with (Eqs.15–16). In the fixed-parameter NUSWIDEOBJ subset experiment, mean solver time including initialization rises from 8.95s at 6,002 samples to 20.51s at 30,000 samples. In the cross-method comparison on the full dataset, PCAL is faster than SMVSC, FPMVS-CAG, and OMSC, which achieve higher ACC. FastMICE is faster and achieves higher NMI, while PCAL achieves higher ACC.
Q5: The authors can give the shortcomings of this work and further study can be presented in Conclusion part. The authors just give that future work will investigate which forms of view heterogeneity benefit most from prior correction and assess computational efficiency under more closely matched preprocessing and parameter-search protocols. How this mentioned future work relates with the proposed work in this paper?
A5: Good question! PCAL learns one correction matrix per view, shared across all samples in that view. This design keeps the correction compact, but limits it to adjusting the anchor grouping at the view level. A systematic feature distortion can shift the anchors across a view, whereas corruption in a small subset of samples can affect the estimated anchors without reflecting a shift that applies to the whole view. These two cases may therefore respond differently to the same correction mechanism. In Table 2, enabling correction on Caltech101-20 improves mean NMI from 0.6050 to 0.6092 while reducing mean ACC from 0.5811 to 0.5679. The ablation establishes that the benefit depends on the metric, but leaves open which types of view heterogeneity make correction useful. We chose to study systematic feature distortion and sample-level corruption separately because they test the assumption underlying PCAL’s design that a single correction shared within a view can capture the relevant deviation. Comparing Full PCAL with DiscreteOnly at fixed settings and across distortion levels would help identify when that assumption holds. A second limitation is that compact correction matrices can still increase solver time. On NUSWIDEOBJ, enabling correction raises the mean runtime from 6.87s to 20.49s, while mean ACC and NMI are unchanged at the reported precision . This motivates measuring the additional solver cost of enabling correction and interpreting it together with the change in clustering quality. For comparisons across methods, the current timings also exclude parameter search, and preprocessing differs across implementations. For example, OPMC standardizes its input before timing. We therefore chose matched preprocessing and tuning budgets as a future direction so that differences in timing can be interpreted under comparable conditions. Reporting preprocessing, tuning, and solver time separately would show where the computational cost arises. We propose replacing the passage beginning with However, the benefits of prior correction at lines 482-485 on page 9 of the submitted manuscript, through the end of the Conclusion, with the following text. Each view uses one correction shared across its samples, so its benefit may depend on the source of view heterogeneity. We will test systematic feature distortion and sample-level corruption separately. Prior correction can also increase solver time. We will measure this overhead and evaluate practical efficiency under matched preprocessing and tuning budgets.
Q1: The novelty of the proposed PCAL is not very clear in Figure 1 and the new parts in this figure can be highlighted. The collections among the part view-specific prior correction, shared anchor representation and discrete cluster assignment should be given in this description for Figure 1.
A1: Good question! PCAL’s contribution is to learn a separate correction to the shared structural prior for each view. In PALCS, the fixed prior Y guides anchor learning, while the view-specific terms enter the graph semantics module. In PCAL, the correction E(v) acts directly on Y, giving each view a corrected prior Y+E(v) for anchor learning. For Figure 1 on page 2 of the submitted manuscript, we propose retaining the three-column PCAL overview and adding a compact PALCS–PCAL comparison beneath it. In the left column, we propose highlighting the View-specific correction and Corrected Priors blocks and labeling the mapping path Guides anchor learning. The bottom comparison will show that the paths from Y and E(v) lead to separate modules in PALCS and merge at Y+E(v) in PCAL. The three PCAL modules are connected through the view-specific anchors A(v) and the shared representation C. First, the mapped prior P(v)(Y+E(v)) provides an alignment target for the anchor update in Eq. 5. The anchors from all views then contribute to the update of C in Eq. 8, together with the current partition through the term λGF. The updated C informs the next prototype and assignment updates in Eqs.12–14. In this way, prior correction influences the partition through the anchors and C, while the current partition feeds back into representation learning. We propose replacing the Figure 1 caption at lines 069–071 on page 2 of the submitted manuscript with the following text. Figure 1. Overview of PCAL. PALCS uses a fixed structural prior to guide anchor learning (Peng et al., 2025). PCAL learns a view-specific correction E(v) to the shared prior Y and uses the mapped code P(v)(Y+E(v)) to guide anchor learning. The learned anchors reconstruct each view through the shared representation C, and the factorization C≈GF couples C to the discrete sample assignments F.
Q2: The authors give the compact view-specific prior correction in 3.2 for prior-corrected anchor learning. PCAL uses a predefined category-anchor grouping matrix Y as a common reference. Constructing this matrix does not require ground-truth sample labels. The mentioned compact view-specific prior correction is not clearly presented for this part, especially how compact can be explained.
A2: Thanks! The predefined matrix Y in Eq.2 groups m anchor positions into k groups, with h=m/k positions in each group. This grouping is constructed from the numbers of clusters and anchors. The sample assignments are learned through F during optimization. The prior correction is compact because each view learns a single k×m correction matrix E(v) shared across all its samples. Equation 10 computes this correction from the difference between the projected anchors (P(v))⊤A(v) and the shared prior Y. Both matrices have size k×m, so each entry of E(v) adjusts the prior for one category–anchor pair. The V corrections therefore require Vkm entries in total, independent of the sample count n for fixed V, k, and$m$ . In the NUSWIDEOBJ scaling experiment, we fix V=5 and k=m=31as the sample count grows from 6,002 to 30,000. The shared representation C grows from 31×6,002 to$31\times 30{,}000$ , while the five correction matrices together contain 5×31×31=4,805 entries at every sample size. This is the specific storage saving of the correction mechanism. We propose replacing the passage beginning with The adjustment concerns the anchor-grouping structure at lines 205–208 on page 4 of the submitted manuscript (Section 3.2) with the following text. Each view learns one k×m correction matrix E(v)shared across its samples, with one entry per category–anchor pair. The V corrections therefore require Vkm entries regardless of the sample count for fixed$V$ , k, and m . As samples are added, C and F each gain one column per sample, while the dimensions of the correction matrices remain fixed.