DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model
This work addresses privacy concerns for users of large language models by enabling distributed fine-tuning, though it is incremental as it builds on existing parameter-efficient fine-tuning methods.
The paper tackles the privacy and computational challenges of fine-tuning large language models in public environments by proposing DLoRA, a distributed parameter-efficient fine-tuning framework that enables collaborative operations between cloud and user devices, achieving significant reductions in computation and communication workload while maintaining superior accuracy and privacy protection.
To enhance the performance of large language models (LLM) on downstream tasks, one solution is to fine-tune certain LLM parameters and make it better align with the characteristics of the training dataset. This process is commonly known as parameter-efficient fine-tuning (PEFT). Due to the scale of LLM, PEFT operations are usually executed in the public environment (e.g., cloud server). This necessitates the sharing of sensitive user data across public environments, thereby raising potential privacy concerns. To tackle these challenges, we propose a distributed PEFT framework called DLoRA. DLoRA enables scalable PEFT operations to be performed collaboratively between the cloud and user devices. Coupled with the proposed Kill and Revive algorithm, the evaluation results demonstrate that DLoRA can significantly reduce the computation and communication workload over the user devices while achieving superior accuracy and privacy protection.