- Rating
- 1
- Confidence
- 4
- Informativeness
- 3(+2)
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes OT-DDC, a multi-view attributed graph clustering framework. The method first applies graph Laplacian smoothing to two feature views and uses MLP encoders to obtain view-specific node representations. It then combines topology-guided contrastive learning with cross-view node-level contrastive learning. Its main module employs entropy-regularized optimal transport (OT) to generate soft cross-view pseudo-labels using both node--prototype feature similarity and degree-based topological costs. Finally, the model jointly constrains feature-space cluster assignments and neighborhood-distribution assignments, and applies -means to the fused representation. The method is evaluated on AMAP, WIKI, Citeseer, and Cora using ACC, NMI, and ARI. The validation includes comparisons with graph clustering baselines, component ablations, an OT ablation, hyperparameter sensitivity analysis, and t-SNE visualizations.
Critical strengths
- The method is intuitive.
- The overall presentation is reasonably clear, and the framework figure helps explain the intended pipeline.
Critical weaknesses
As far as I know, this work has no substantive innovation. Entropy-regularized OT pseudo-labeling, swapped prediction, DEC-style target sharpening, and neighborhood-distribution regularization are established techniques. The paper mainly combines these components, but does not clearly establish a substantial difference from the closest related methods.
I don't see what's interesting about this work. Also, the paper says "extensive experiments" in many places, but with only 4 datasets, that doesn't deserve to be called extensive experiments. I'm not asking the authors to add more experiments, I just think there's some overclaiming here. They could just say "multiple datasets" instead of "extensive experiments." By the way, formulas that are not cited do not need numbering.
Questions for authors
-
How are and constructed for the four datasets? What is the exact formula for the claimed frequency-domain view?
-
Are the MLP encoders shared across views or independently parameterized?
-
How is computed? What graph or topological structure is associated with a prototype?
-
What is the update rule for ? If is non-uniform, in what sense are the resulting assignments globally balanced?
-
Is used in Eq. (12)? If not, how is the KL divergence defined for unnormalized logits?
-
How is the hard assignment matrix in Eq. (17) obtained and updated? Is it detached from the computational graph?
-
What pseudo-label generation method is used in the ``w/o OT'' variant?
ICLR Rebuttal: Please Submit Your Response Soon
This is a reminder that the ICLR rebuttal period is ending soon. I would appreciate it if the authors could submit their response as soon as possible so that I can finalize my review.