AFLoRA: Adaptive LoRA for Resource-Efficient Federated Fine-Tuning of Large Language Models
AFLoRA, an adaptive LoRA-based resource-efficient federated fine-tuning framework, introduces diagonal-based dynamic rank assignment, which dynamically adjusts local LoRA ranks based on client resources and local adaptation state guided by a learnable diagonal matrix and develops a zero-padding-based rank-aware aggrega...
Ya-Jie Zhou, Xia-Yi Pang, Zhi-Bo Wang et al.
· IEEE Transactions on Mobile... · 0 citations