- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a clustering framework that establishes shared prototypes for heterogeneous datasets, named CPC. Specifically, Cross-Dataset Prototype Alignment first projects heterogeneous datasets into a common space and then learns a shared prototype codebook. After that, Representative Prototype Discovery constructs interactions among activated prototypes and selects representative ones as cluster centers. Experiments on various clustering datasets demonstrate the effectiveness of the proposed CPC.
Critical strengths
-
The paper addresses an important problem in clustering, namely learning common prototypes for heterogeneous datasets.
-
Experiments on various datasets demonstrate the effectiveness of the proposed CPC.
-
The paper is well structured and clearly written.
Critical weaknesses
-
My main concern is the motivation of this work. To be honest, in traditional classification tasks, I think the weight vectors of the linear classification layer could be considered cluster centers, which are first learned from large-scale data and then applied to various downstream datasets. Therefore, I do not think that explicitly constructing shared prototypes for heterogeneous datasets is an entirely new setting. The authors should discuss this and address my concern.
-
As discussed in Weakness 1, shared prototypes could potentially be obtained through the linear layer. I wonder why the proposed method requires more complex components to establish shared prototypes, such as dataset-specific adapters and a shared Transformer encoder. The authors should provide theoretical or empirical evidence to verify the effectiveness of these components.
-
The proposed method appears to be incremental. Specifically, the authors should clarify the differences between the four objectives in the first stage and existing representation learning objectives, such as the commitment loss in VQ-VAE and BYOL, the contrastive loss in SimCLR, and the entropy regularization in Contrastive Clustering. Given that the novelty of the setting is questionable, it is difficult for me to recognize the contribution of this work unless the authors could clarify the novelty of the proposed methods.
-
Following Weakness 3, the proposed CPC integrates seven loss terms, which remains unclear that whether each loss could work with a distinct and necessary purpose. In particular, the paper does not provide any ablation study to clarify the individual contribution of each term.
-
I also have concerns about the experiments. It is recommended to evaluate the proposed CPC on widely used benchmarks such as ImageNet or CIFAR-100. To be honest, I am quiet unfamiliar with the datasets in this paper, thus I think that the authors should clarify the sources of these datasets and justify whether they could searve as benchmarks for evaluating deep clustering methods.
Questions for authors
See the weaknesses.
Dear reviewers and authors,
As the discussion period is limited, please follow up on the latest responses and comments in a timely manner to address any remaining concerns. Thank you!