SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA

• URL: http://arxiv.org/abs/2505.23724v1
• Date: Thu, 29 May 2025 17:55:21 GMT
• Title: SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
• Authors: Minrui Luo, Fuhang Kuang, Yu Wang, Zirui Liu, Tianxing He,
• Abstract summary: Subspace-Constrained LoRA (SC-LoRA) is a novel LoRA framework engineered to navigate the trade-off between efficient fine-tuning and knowledge preservation.<n>In our experiments, SC-LoRA succeeds in delivering superior fine-tuning performance while markedly diminishing knowledge forgetting.
• Score: 15.095035820064028
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), are indispensable for efficiently customizing Large Language Models (LLMs). However, vanilla LoRA suffers from slow convergence speed and knowledge forgetting problems. Recent studies have leveraged the power of designed LoRA initialization, to enhance the fine-tuning efficiency, or to preserve knowledge in the pre-trained LLM. However, none of these works can address the two cases at the same time. To this end, we introduce Subspace-Constrained LoRA (SC-LoRA), a novel LoRA initialization framework engineered to navigate the trade-off between efficient fine-tuning and knowledge preservation. We achieve this by constraining the output of trainable LoRA adapters in a low-rank subspace, where the context information of fine-tuning data is most preserved while the context information of preserved knowledge is least retained, in a balanced way. Such constraint enables the trainable weights to primarily focus on the main features of fine-tuning data while avoiding damaging the preserved knowledge features. We provide theoretical analysis on our method, and conduct extensive experiments including safety preservation and world knowledge preservation, on various downstream tasks. In our experiments, SC-LoRA succeeds in delivering superior fine-tuning performance while markedly diminishing knowledge forgetting, surpassing contemporary LoRA initialization methods.

Related papers

• LoRA Is Slower Than You Think [0.0]
  Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs)<n>By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that need to be updated.<n>We observed that LoRA does not consistently provide speed improvements across all model architectures and training setups.
  arXiv  Detail & Related papers  (2025-07-06T08:36:43Z)
• Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA [35.64232606410778]
  Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks.<n>We re-examine memorization in fine-tuning and uncover a surprising divergence from prior findings across different fine-tuning strategies.<n>Using a more relaxed similarity-based memorization metric, we demonstrate that LoRA significantly reduces memorization risks compared to full fine-tuning.
  arXiv  Detail & Related papers  (2025-06-25T22:01:25Z)
• LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models [61.96237184081951]
  Low-Rank Adaptation (LoRA) is widely used to efficiently acquire specialized knowledge in Multimodal Large Language Models (MLLMs)<n>LoRA introduces substantial harmful redundancy during visual instruction tuning, which exacerbates the forgetting of general knowledge and degrades downstream task performance.<n>We propose LoRASculpt to eliminate harmful redundant parameters, thereby harmonizing general and specialized knowledge.
  arXiv  Detail & Related papers  (2025-03-21T04:31:09Z)
• How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? [55.33467849079774]
  Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models.<n>We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-02-20T12:31:03Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models [19.533062623518674]
  This paper critically analyzes the convergence and performance guarantees of popular FL frameworks utilizing Low-Rank Adaptation (LoRA)<n>We demonstrate that direct weight averaging outperforms LoRA-based strategies, leading to superior performance for fine-tuned models.<n>Our findings show that GaLore along with direct-weight aggregation is a more effective approach, outperforming federated LoRA methods like FlexLoRA and FFA-LoRA across both text and image modalities.
  arXiv  Detail & Related papers  (2024-10-30T15:23:44Z)
• Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning [65.31677646659895]
  Large language models demonstrate impressive performance on downstream tasks, yet they require extensive resource consumption when fully fine-tuning all parameters.<n>We propose a framework to clearly define task-specific directions (TSDs) and explore their properties and practical utilization challenges.<n>We then introduce a novel approach, LoRA-Dash, which aims to maximize the impact of TSDs during the fine-tuning process.
  arXiv  Detail & Related papers  (2024-09-02T08:10:51Z)
• Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models [51.20476412037321]
  We propose Safe LoRA, a simple one-liner patch to the original LoRA implementation by introducing the projection of LoRA weights from selected layers to the safety-aligned subspace.<n>Our experiments demonstrate that when fine-tuning on purely malicious data, Safe LoRA retains similar safety performance as the original aligned model.
  arXiv  Detail & Related papers  (2024-05-27T05:04:05Z)
• Improving LoRA in Privacy-preserving Federated Learning [44.47315926976059]
  Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models. This paper proposes an efficient and effective version of LoRA, Federated Freeze A LoRA (FFA-LoRA), to alleviate these challenges.
  arXiv  Detail & Related papers  (2024-03-18T23:20:08Z)
• DoRA: Weight-Decomposed Low-Rank Adaptation [57.68678247436207]
  We introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA) DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning.
  arXiv  Detail & Related papers  (2024-02-14T17:59:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.