- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The authors identify a personalization coverage–coordination gap in representative personalized federated LoRA designs: personalization remains centered on representation adaptation, while decision-level adaptation and the coordination of shared and local components are not jointly organized. To solve this, they propose FedRDAC, integrating RDDA to extend client-specific adaptation across representation and decision levels and AGLC to adaptively coordinate shared and personalized components during local training.
Critical strengths
- This paper is well written and easy to follow.
- The motivation of this work is clear, i.e., identifying a personalization coverage–coordination gap in representative personalized federated LoRA designs and proposing a new method to solve it.
Critical weaknesses
- The “coverage–coordination gap” is mainly a description, not yet a tested rule. This work explains the gap, but it does not provide experimental results that predict when a local task head or adaptive coordination will help. Experiments where a local head is not needed, or comparisons with a parameter-matched local-head-only method, would better support the claimed reason for the gains.
- The experiment's scope is limited. The experiments use only SST-2 and MRPC, one RoBERTa-base model, and a small number of clients. More experiments on other tasks, such as language generation tasks and coding tasks, more model families, such as Qwen and Llama, and more client numbers, are needed.
- The proposed method lacks explanatory proof. How can it be proved that the proposed method truly captures the shared and specific parts? Some experimental proofs or theoretical explanations are needed.
Questions for authors
- Are the results averaged over several random seeds and client splits? Please report standard deviations or confidence intervals.
- How does FedRDAC perform on more GLUE tasks, generation tasks, larger language models, and more clients?
- How were the “inspired” baselines tuned, and can you compare with official implementations when they exist?
- What is the memory cost of keeping local LoRA branches and heads on clients, compared with other personalized FL methods?