Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity

Abstract: Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of LLMs, significantly reducing computational costs. By adjusting ranks for each client, federated LoRA enables flexible resource allocation. However, we observe that heterogeneous ranks among clients lead to unstable performance. Our analysis attributes this instability to the conventional zero-padding aggregation strategy, which dilutes information from high-rank clients during model aggregation. To address this issue, we propose a replication-based padding strategy that better retains valuable information from clients with high-quality data. Empirically, this approach accelerates convergence and enhances the global model's predictive performance.