RA-LoRA: Rank-Aware Aggregation for Low-Rank Adaptation with Federated Fine-Tuning

ACL ARR 2025 July Submission675 Authors

Abstract: Federated fine‑tuning of foundation models is impeded by the need to communicate billions of parameters. Low‑rank adaptation (LoRA) alleviates this by updating only compact adapter matrices. However, varying client device capabilities lead to different adapter ranks, causing rank heterogeneity that undermines aggregation, and existing reconciliation methods still incur bias or inefficiency. To address this challenge, we propose RA-LoRA, a principled rank‑aware aggregation framework that decomposes each update into rank‑wise components and aligns them using analytically derived weights. Experiments on both language models and vision transformers demonstrate consistent accuracy improvements in one‑shot and three‑shot settings.

Paper Type: Short

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: parameter-efficient-training, data-efficient training, NLP in resource-constrained settings

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Discussed in Section 7

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Cited in Section 4 and References

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Discussed in Section 4

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Section 4

B4 Data Contains Personally Identifying Info Or Offensive Content: Yes

B4 Elaboration: Section 4

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Appendix

B6 Statistics For Data: Yes

B6 Elaboration: Section 4, Table 1

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section 4, Appendix B

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section 4, Appendix B

C3 Descriptive Statistics: Yes

C3 Elaboration: Table 1, 2

C4 Parameters For Packages: Yes

C4 Elaboration: Section 4 (FedIT framework)

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: No

E1 Elaboration: We used ChatGPT only for correcting gramatical errors.

Author Submission Checklist: yes

Submission Number: 675