DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution
Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of downstream tasks. Existing parameter-efficient fine-tuning (PEFT) methods such as Low-Rank Adaptation (LoRA) rely on a bypass framework that ignores the differential parameter budget requirements across weight matrices, which may lead to suboptimal fine-tuning outcomes. To address this issue, we introduce the Dynamic Low-Rank Adaptation (DoRA) method. DoRA decomposes high-rank LoRA layers into structured single-rank components, allowing for dynamic pruning of parameter budget based on their importance to specific tasks during training, which makes the most of the limited parameter budget. Experimental results demonstrate that DoRA can achieve competitive performance compared with LoRA and full model fine-tuning, and outperform various strong baselines with the same storage parameter budget. Our code is available at https://github.com/MIkumikumi0116/DoRA
Code (4)
Tasks
parameter-efficient fine-tuningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA
Recent advancements in Generative AI have significantly improved the efficiency and adaptability of natural language processing (NLP) systems, particularly through Retrieval-Augmented Generation (RAG), Low-Rank Adaptatio…
Domain Adaptationparameter-efficient fine-tuningRAGRetrieval-augmented GenerationEDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition
Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their learning pattern and full fine-tuning. T…
parameter-efficient fine-tuningDoRA: Weight-Decomposed Low-Rank Adaptation
Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accurac…
parameter-efficient fine-tuningDoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the le…
parameter-efficient fine-tuningBiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation
Parameter-efficient fine-tuning (PEFT) of large language models (LLMs) has gained considerable attention as a flexible and efficient way of adapting LLMs to downstream tasks. Among these methods, weighted decomposed low-…
Natural Language Understandingparameter-efficient fine-tuningText Generationtoken-classification+1