- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper addresses an important problem of optimization of distributed devices in federated learning, and proposes PP-EFLS that incorporates multiple local steps into federated learning optimization framework. The proposed method helps to solve the challenges in the joint treatment of partial participation schemes. The paper presents a nonconvex convergence bound and evaluates the method on CIFAR-10 with ResNet-18 under different levels of data heterogeneity, numbers of local steps, and client-selection strategies. The reported partial-participation experiments show accuracy improvements over FedAvg and FedProx.
Critical strengths
- A practically well-motivated problem is studied to investigate the joint treatment in partial participation schemes.
- The authors studied additional analytical challenges for introducing multiple local steps and provide theoretical bounds addressing this interaction between participation, heterogeneity and others.
- The reported accuracy gains over FedAvg and FedProx are encouraging.
Critical weaknesses
- Some parts in theoretical analysis are not straightforward or clear enough for me. Some are listed in the 'Questions For Authors' section below as examples.
- The range of baselines is limited. More comparisons with recent federated learning optimization method would significantly strengthen the paper, such as FAST [1] and FedAU [2].
Reference
[1] Zhe Li, Seyedsina Nabavirazavi, Bicheng Ying, Sitharama Iyengar, and Haibo Yang. FAST: A Lightweight Mechanism Unleashing Arbitrary Client Participation in Federated Learning. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2025.
[2] Shiqiang Wang and Mingyue Ji. A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging. International Conference on Learning Representations (ICLR), 2024.
Questions for authors
- The lower bound in inequality (22) appears without detailed justification. It seems that some special selection of parameters could lead to violation of the lower bound. Could you please provide detailed derivation of the bound?
- For controlling stochastic terms (on page 15-16), I think it requires a smoothness on each . However the assumption only ask for a global smoothness for the objective . Is it guaranteed by derivation or are those objectives assumed to be the same function?
- The proposed algorithm extends PPBC with multiple local steps. Does LS1 in Table 1-6 exactly recover PPBC? If not, providing evaluation of PPBC and comparison will strengthen the contribution of the proposed algorithm.
- Since there are extra uploads for correction in your algorithm, is it fair to compare with baselines FedAvg and FedProx in your main results from Table 1 to 6 with the fixed 100 epochs?