- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposed the SGE-softmax method, which replaces the independent Bernoulli readout mechanism of SGE with softmax, and establishes the joint convexity of the method. Through domain-incremental and class-incremental benchmarks on the MNIST and CIFAR-100 datasets, the authors investigate when input-dependent gating mechanisms become effective, suggesting that empirical gating margins primarily emerge under conditions characterized by a regime structure.
Critical strengths
- The paper improves the SGE method using softmax, it is simple and effective.
- The paper implements experiments on class-incremental and domain-incremental scenarios, validating the method's effectiveness from different perspectives.
Critical weaknesses
- The novelty of the paper is limited. The authors' contribution only is modifying SGE using softmax to handle multi-class classification.
- SGE employs a set of hyperplanes to reduce the number of parameters. How are it initialized? What is the impact of different initialization methods? Why is using a set of hyperplanes still viable?
- The proposed method lacks comparisons with state-of-the-art methods (such as PTM, DER, and Tagfex), undermining the persuasiveness of its effectiveness for continual learning.
- The performance of the proposed method remains limited in class-incremental tasks.
- The paper reports only accuracy as an evaluation metric for continual learning, which is insufficient to demonstrate effectiveness. Since the authors claim GDN mitigates catastrophic forgetting, reporting metrics such as Forgetting, Forward Transfer (FWT), and Backward Transfer (BWT) would better illustrate the model's ability to handle the issue.
- There is no comparison regarding parameter counts in this work. Compared to other methods, is the performance gain simply a result of an increase in model parameters?
Questions for authors
Please refer to the weakness.