- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper focuses on decentralized cross-client federated learning for medical image segmentation. Instead of relying on a central server for model aggregation, FedOPS adopts a sequential cross-client training paradigm in which model parameters are directly transmitted among clients. The method mainly addresses two issues: the client training order may affect knowledge propagation and convergence stability, and unstable or interfering parameter updates may be propagated across clients. To address these issues, the authors introduce two components. First, Consistency-aware Client Scheduling (CCS) orders clients according to the similarity of their feature representations so that similar clients are trained consecutively. Second, Cross-client Parameter Sanitization (CPS) evaluates the historical update-direction consistency of each trainable parameter and generates a binary mask to preserve relatively stable parameters while filtering unstable ones before transmission to the next client. The framework is built on SAM, with the pretrained encoder frozen and only the adapters and decoder being trained and transmitted. Experiments are conducted on Prostate, Fundus, and Nuclei segmentation datasets, with comparisons against FedUNet, FedCross, FedSAM, FedMSA, and TM-FAL, together with ablation studies on CCS and CPS.
Critical strengths
- The paper addresses the practical problem of unstable sequential cross-client training under heterogeneous data distributions.
- FedOPS has a simple and modular design that separates client scheduling (CCS) from parameter filtering (CPS).
- The method is computationally lightweight by freezing the SAM encoder and training and transmitting only the adapters and decoder.
- The experimental evaluation is relatively comprehensive, covering three medical image segmentation benchmarks and several federated learning baselines.
- The paper provides useful ablation and analysis experiments on CCS, CPS, backbone choice, the threshold parameter, communication rounds, and model complexity.
Critical weaknesses
-
The CCS is an incremental extension of FedCross that adds feature-similarity-based client reordering, while the reformation is limited.
-
The construction of the client feature representation used by CCS is insufficiently described, including its extraction, aggregation, and update strategy.
-
The paper contains terminology inconsistencies, for example, using different full names for CCS and CPS in the main text and the caption of Figure 2.
Questions for authors
- How is the client feature representation used by CCS extracted, aggregated across local samples, and updated during training?
- Is the client training order fixed before training or recomputed across communication rounds as client representations change?
- Could independent parameter-wise masking in CPS disrupt coordinated updates among correlated parameters and introduce additional update drift?