FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918528979828736 |
|---|---|
| author | Wang, Zehao Yang, Guanglei Zeng, Yihan Xu, Hang Zhang, Hongzhi Zuo, Wangmeng Feng, Chun-Mei |
| author_facet | Wang, Zehao Yang, Guanglei Zeng, Yihan Xu, Hang Zhang, Hongzhi Zuo, Wangmeng Feng, Chun-Mei |
| contents | Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data locality. However, the direct combination of FedAvg and LoRA suffers from three key issues: limited update space, which restricts the model's effective learning capacity; inter-round state mismatch, which disrupts cross-round local optimization continuity; and a client-agnostic starting state, which slows local convergence on clients. Although recent methods mitigate the limited update space issue by merging LoRA updates into the backbone across communication rounds, inter-round state mismatch and the client-agnostic starting state remain insufficiently addressed. To address these issues, we propose FedSmoothLoRA, a federated LoRA tuning framework that preserves the enlarged update space, improves cross-round local optimization continuity, and provides a client-aware starting state for local training. At each communication round, FedSmoothLoRA constructs the local LoRA initialization using two matrices: a Round-Matching matrix that preserves cross-round local state continuity, and a Gradient-Aligned matrix that provides client-specific optimization guidance from gradient signals estimated on local data. Together, these designs enable smoother and faster convergence. Extensive experiments on image classification and natural language generation tasks demonstrate that FedSmoothLoRA consistently outperforms existing federated LoRA tuning methods. Code: https://github.com/wangzehao0704/FedSmoothLoRA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation Wang, Zehao Yang, Guanglei Zeng, Yihan Xu, Hang Zhang, Hongzhi Zuo, Wangmeng Feng, Chun-Mei Computer Vision and Pattern Recognition Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data locality. However, the direct combination of FedAvg and LoRA suffers from three key issues: limited update space, which restricts the model's effective learning capacity; inter-round state mismatch, which disrupts cross-round local optimization continuity; and a client-agnostic starting state, which slows local convergence on clients. Although recent methods mitigate the limited update space issue by merging LoRA updates into the backbone across communication rounds, inter-round state mismatch and the client-agnostic starting state remain insufficiently addressed. To address these issues, we propose FedSmoothLoRA, a federated LoRA tuning framework that preserves the enlarged update space, improves cross-round local optimization continuity, and provides a client-aware starting state for local training. At each communication round, FedSmoothLoRA constructs the local LoRA initialization using two matrices: a Round-Matching matrix that preserves cross-round local state continuity, and a Gradient-Aligned matrix that provides client-specific optimization guidance from gradient signals estimated on local data. Together, these designs enable smoother and faster convergence. Extensive experiments on image classification and natural language generation tasks demonstrate that FedSmoothLoRA consistently outperforms existing federated LoRA tuning methods. Code: https://github.com/wangzehao0704/FedSmoothLoRA |
| title | FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.29460 |