- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In this work, the authors propose FedCoIn, a federated learning framework designed to address noisy labels. FedCoIn consists primarily of two modules: the first is a global generative modeling approach that enables collaborative noise correction across clients, while the second incorporates distribution-aware dynamic priors and a noise-aware weighted aggregation strategy. The authors provide a convergence analysis for three different heterogeneity settings. Experimental results demonstrate that FedCoIn consistently outperforms state-of-the-art methods across various scenarios involving heterogeneous noise.
Critical strengths
-
The structure of this paper is clear and reasonable.
-
The paper addresses both the discrepancies in client data distribution and the variations in label noise, which is of practical significance.
-
The paper provides comprehensive theoretical analysis, ensuring the robustness of the proposed method.
Critical weaknesses
-
Equation (4) shows that minimizing the posterior KL divergence is equivalent to maximizing the ELBO. However, Equation (5) instead features the term . Need to clarify the negative ELBO objective.
-
Is the initial classifier a local model or a global model? While Figure 1 clearly illustrates the aggregation of global parameters for the initial classifier, the main text and the algorithm description only state that each client trains its own classifier and subsequently freezes its parameters, without explicitly mentioning this aggregation step.
-
Why is the non-IID performance of FedClean not shown in Table 2?
-
Does w/o CoIn mean removing all generated inferences, or only removing the collaborative steps?
-
In the legends for Figures 3(a,b), the method is labeled as FedCoGen.
Questions for authors
See in weakness.
Thank you for your rebuttal. I will keep my positive rating.