← Back to all news
arXiv AI By Lei Wang, Jieming Bian, Letian Zhang, Jie Xu

Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity

Read the original on arXiv AI →

The paper introduces FedRoRA, a federated learning framework that combines Low‑Rank Adaptation (LoRA) with rank‑heterogeneous personalization. It separates model adaptation into shared global directions and client‑specific rank‑wise magnitudes, using SVD on the server to extract a global subspace and a personalized projection with top‑k selection for each client. Experiments on natural language understanding and generation tasks show that FedRoRA outperforms existing state‑of‑the‑art methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 16

SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients

arXiv:2601. 11219v3 Announce Type: replace-cross Abstract: Federated learning (FL) for large language models (LLMs) has attracted increasing attention as a privacy-preserving approach for adapting models over distributed data, where parameter-efficient methods such as Low-Rank Adaptation (LoRA) are widely adopted to reduce communication and memory costs.

By Zhikang Shen, Jianrong Lu, Haiyuan Wan, Jianhai Chen
llmsfine-tuningbenchmarkssafety
More like this →
arXiv AI
Aug 18

FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA

arXiv:2608. 15381v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of large language models, but its factorized parameterization creates a tension between accurate aggregation of local updates and continuity of locally optimized factors.

By Juseok Jeon, Ramy E. Ali, Doyun Kwon, Myungbeom Her, Jinhwi Kim, Jinhyun So
llmsfine-tuning
More like this →