ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning
This paper revisits alternating low-rank updates for federated fine-tuning and examines their behavior in decentralized federated learning (DFL). While alternating the LoRA matrices has been shown to stabilize aggregation in centralized FL, extending this mechanism to decentralized, peer-to-peer communication introduces new challenges due to phase-state mismatch and block-wise divergence across clients. We introduce ADF-LoRA, which synchronizes the update of only one low-rank matrix per round and mixes both matrices to maintain more consistent parameter states under decentralized propagation. This design preserves the cross-term suppression effect of alternating updates while improving stability in serverless topologies. We provide a convergence analysis under standard smoothness assumptions and evaluate ADF-LoRA on multiple GLUE tasks. Experiments show that ADF-LoRA achieves faster and smoother convergence and delivers the highest average accuracy across tasks, outperforming existing LoRA variants in decentralized FL by a consistent margin.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA
Decentralized federated learning (DFL), a serverless variant of federated learning, poses unique challenges for parameter-efficient fine-tuning due to the factorized structure of low-rank adaptation (LoRA). Unlike linear…
parameter-efficient fine-tuningFederated LearningBeyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
Federated LoRA enables parameter-efficient adaptation of large language models under decentralized data and limited client resources.However, directly averaging LoRA factors is representation-dependent: the same intrinsi…
DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation
Integrating low-rank adaptation (LoRA) with federated learning (FL) has received widespread attention recently, aiming to adapt pretrained foundation models (FMs) to downstream medical tasks via privacy-preserving decent…
Federated LearningPrivacy PreservingFedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data. In practice, however, a discrepancy between the factor-wise averaging used to preserve low rank and…
Natural Language UnderstandingTowards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients
Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank Adaptation (LoRA) has been proposed as a …
Federated Learning