- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The submission studies whether systematic differences in view-local semantics can be exploited for clustering rather than simply discouraged. Its method, CAST, learns class-conditional transitions between a shared partition and local semantic states represented by independent anchor graphs. The evaluation combines eight public benchmarks, eleven comparison methods, two controlled shift mechanisms, transition-channel ablations, unequal-anchor experiments, and view-wise semantic diagnostics. The reported results support the usefulness of semantic calibration on both ordinary and deliberately shifted data, with additional experiments examining which aspects of the transition model matter.
Critical strengths
First, Table 1 makes a persuasive empirical case for the semantic-shift hypothesis by combining results on the original benchmarks with controlled Euclidean and spherical shifts. The central idea is that views can share a global partition while their local semantics differ systematically. CAST is already among the strongest methods on the original data, making it relevant to routine clustering. The YTF results after the controlled shifts are particularly informative: on YTF10, ACC rises from 88.41% to 97.59% and 96.87%, and YTF20 and YTF50 also improve. I find this evidence convincing because it fits the explanation that systematic semantic changes can preserve useful class information and sometimes produce structure that a calibrated model can use more effectively.
Second, the mechanism is examined through complementary structural ablations and semantic diagnostics. On unmodified MSRC and YTF10, Table 3 shows substantial gains over Identity, supporting the relevance of naturally occurring semantic discrepancies in heterogeneous handcrafted representations. Under controlled shifts, full CAST generally does better than the restricted transition variants; some restrictions even perform worse than Identity. These comparisons provide good evidence that class-dependent shift rates and destination distributions serve complementary purposes, and that the chosen parameterization of has an appropriate level of expressiveness for systematic shifts. The semantic diagnostics in Figures 2 and 3 complement these ablations: view-wise ACC, mean semantic preservation, and normalized semantic information follow broadly similar trends. Their departures from exact agreement also make sense given the theoretical distinction between preserving semantics and retaining class information.
Critical weaknesses
My main reservation concerns how the experiments are reported. I would like the numerical shift settings, the order of preprocessing and graph construction, and the tuning and randomization behind the five-run means to be described together more clearly for reproducibility. A measure of dispersion would also help me judge the close comparisons.
For Table 4, I would like to see the selected anchor-count configurations for each view and a short discussion of why the gains vary across datasets. The ability to accommodate heterogeneous anchor graphs remains useful even when the performance change is small.
Questions for authors
-
For Table 1 and Figures 2 to 5, could the authors give a small configuration table listing , the affected views, and any view left unchanged? Are these settings shared across datasets?
-
Could the authors spell out the sequence of feature preprocessing, shift generation, any preprocessing after the shift, and anchor-graph construction? I would especially like to know when sample-wise normalization is applied in the spherical and Euclidean settings, and whether anchors and assignments are rebuilt from the transformed features or partly reused. If Euclidean relocation is followed by sample-wise normalization, which stage does the within-subgroup distance-preservation statement refer to?
-
I would like to understand what "best mean performance over five runs" means here. Are hyperparameters and anchor counts searched separately for each shifted condition, or carried over from the original data? How is the final configuration chosen for each method, and how is the selection rule kept consistent across methods?
-
Which random choices are made when generating shifts, constructing anchor graphs, and initializing CAST? Please give the seed lists or a deterministic generation rule, and say whether the predefined seeds are shared across datasets or specified separately. Across the five runs, are the perturbed data and graphs fixed, or is either regenerated? This would make clear which sources of randomness the reported means cover.
-
A standard deviation, range, or another compact dispersion statistic from the existing runs would make the close comparisons easier to judge. It would also help assess whether the main full-versus-restricted transition conclusions recur across runs.
-
For Table 4, what are the selected configurations, and how were they chosen? Where there is little or no gain, is the common count already sufficient, is performance near saturation, or do the views gain little from different representation sizes? The flexibility to accommodate heterogeneous graphs remains useful in its own right, even where individual metrics do not improve.
2 comments
Response to Question 4:
To generate shifts, we draw a separate within-class sample ordering for each affected view. For each source class in that view, one target class is sampled uniformly from the other classes, and all selected observations from that source class use this target. Different source classes may share a target.
Randomness also enters through the initial anchors and sample-to-anchor assignments in graph construction and the spherical K-means starts used to initialize CAST. For reproducibility and fair comparisons, we fix the random seed at 1 across all datasets for shift generation, graph construction, and CAST fitting. The transition variants follow the same initialization rule for paired comparisons.
Within a CAST call, spherical K-means is run with ten starts for each view. These starts use successive draws from that call's random stream, and the solution with the largest within-cluster cosine objective initializes the view's local components.
Shifted observations are generated once per dataset and condition. Graphs are constructed once per candidate configuration and reused by the five fits and the paired transition variants. The reported means therefore measure repeatability under fixed inputs and initialization. Figures 2–5 use a single fit at the corresponding selected configuration.
Response to Question 5 and Weakness 1:
For the reported five-run experiments, the standard deviations of ACC, NMI, and ARI are all 0. This includes both full-transition settings, CAST with and , and the restricted transition variants. Under the protocol described above, the reported metric differences and full-versus-restricted rankings are identical across all five repetitions, including the close comparisons.
Response to Question 6 and Weakness 2:
For CAST-H, each view has the candidate set . We search the full Cartesian product , considering all combinations. The selected configuration maximizes five-run mean ACC; NMI and ARI are computed from the same predicted labels used to obtain the best ACC. The counts, in original view order, are:
| Dataset | Selected |
|---|---|
| EuroSAT | |
| MSRC | |
| RSICB128 | |
| YTF10 | |
| YTF20 | |
| YTF50 | |
| CIFAR10 | |
| CIFAR100 |
Anchor counts control the granularity of each view's representation. Different feature geometries can benefit from different granularities, so a common count can be suitable for some views while being less suitable for others.
The selected unequal counts improve YTF20 from 76.49% to 79.76% ACC and from 65.88% to 72.71% ARI; YTF10 improves from 76.74% to 84.86% ARI.
The revised MSRC-v6 comparison will use the same default environment as the other experiments. The earlier 95.71% ACC was obtained on an Intel Core i7-14700 with MATLAB R2023b. After correction, CAST still ranks first on MSRC-v6 in Table 1. The Table 4 comparison uses the following two configurations.
| Method | Anchor counts | ACC / NMI / ARI (%) |
|---|---|---|
| CAST | 93.81 / 87.43 / 86.13 | |
| CAST-H | 95.24 / 90.69 / 88.73 |
The gains are 1.43, 3.26, and 2.60 percentage points, respectively.
Equal-count configurations are also included in the search. CIFAR10 selects , the standard CAST configuration, and retains its 99.07% ACC. This is consistent with a common count already being sufficient within the tested grid and limited remaining performance headroom. CAST-H accommodates independently constructed heterogeneous graphs even when the selected configuration or a particular metric does not improve.
Response to Question 1:
For both controlled transformations, δ is the fraction selected from each source class and η controls the transformation strength. We use δ=0.5 and η=1 across all datasets. In each affected view, round(0.5nc) observations are selected from source class c. The selected observations receive the full source-to-target centroid displacement in the Euclidean setting or the full source-to-target angular displacement in the spherical setting.
The indices follow the original view order.
Response to Question 2:
Both controlled conditions apply sample-wise normalization before and after the shift:
\longrightarrow \ell_2\text{ normalization} \longrightarrow \text{Euclidean relocation or spherical rotation} \longrightarrow \ell_2\text{ normalization} \longrightarrow \text{new anchors and assignments} \longrightarrow \text{CAST}.$$ Both the anchors and the sample-to-anchor assignments are constructed from the transformed, normalized features. Selected observations from the same source class and view receive the same displacement, so $\widetilde x_i^{(v)}-\widetilde x_j^{(v)}=x_i^{(v)}-x_j^{(v)}$. Their pairwise distances and centered covariance are preserved at that step. Subsequent sample-wise normalization can change those distances. Spherical rotation preserves norms and inner products within the subgroup receiving the same orthogonal transformation. Its inputs already have unit norm, so the subsequent normalization preserves this geometry up to numerical precision. **Response to Question 3:** The original, Euclidean-shift, and spherical-shift conditions are tuned separately. For standard CAST, the common anchor count is searched over $m\in\\{C,2C,3C\\}$, with $m_v=m$ for every view. At each candidate configuration, ACC is averaged over five fits. The configuration with the highest mean ACC is selected, and the reported NMI and ARI are computed from the same predicted labels used to obtain the best ACC. Anchor-based comparison methods use the same anchor-count candidate set; their other method-specific hyperparameter ranges follow their original papers. The mean-ACC selection rule is shared across methods. Table 3 reuses the selected CAST configuration for each dataset and condition, fixing the graphs and non-transition settings across the transition variants. Each variant is fitted five times.