HRP: High-Rank Preheating for Superior LoRA Initialization

• URL: http://arxiv.org/abs/2502.07739v3
• Date: Mon, 26 May 2025 08:53:14 GMT
• Title: HRP: High-Rank Preheating for Superior LoRA Initialization
• Abstract summary: High-Rank Preheating (HRP) trains Low-Rank Adaptation (LoRA) with a higher preheating rank for a few steps.<n>HRP significantly enhances LoRA's effectiveness in various models and tasks.
• Score: 58.3319586613105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies the crucial impact of initialization in Low-Rank Adaptation (LoRA). Through theoretical analysis, we demonstrate that the fine-tuned result of LoRA is highly sensitive to initialization, which is likely to lead suboptimal low-rank results. While this issue can be mitigated by adjusting the initial direction towards the main singular vectors of the target $\Delta W$, which is, however, typically unknown in real-world scenarios. To approximate this initial direction, we propose High-Rank Preheating (HRP), which first trains LoRA with a higher preheating rank for a few steps, then uses the main singular vectors of the derived $BA^\top$ as initialization for the main fine-tuning process. With only a modification in the initial direction, we prove that HRP makes LoRA achieve better fine-tuned results than random initialization in expectation, and the enhancement grows with the preheating rank. We validate our theoretical findings through extensive experiments in various models and tasks, where HRP significantly enhances LoRA's effectiveness and outperforms other initialization strategies and other LoRA variants.

Related papers

• TaRA: Training-Aware Low-Rank Adaptation Initialization [15.468502643386962]
  Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning.<n>Training-aware Low-Rank Adaptation Initialization (TaRA) is a method that initializes LoRA such that the gradients induced by the low-rank factors closely approximate the gradient of the corresponding full-rank weight matrix.
  arXiv  Detail & Related papers  (2026-09-02T14:15:22Z)
• Statistical Inference for Rank Allocation in Low-Rank Adaptation [54.886931928255564]
  Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models.<n>We propose StatLoRA, a statistical inference-based rank allocation method.<n>We show that StatLoRA achieves comparable or better performance than vanilla LoRA, AdaLoRA, and I-LoRA under matched rank budgets.
  arXiv  Detail & Related papers  (2026-07-22T14:25:59Z)
• LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules [10.00294036303927]
  We introduce LoRA-Squeeze, a simple and efficient methodology that aims to improve standard LoRA learning.<n>Our approach posits that it is better to first learn an expressive, higher-rank solution and then compress it, rather than learning a constrained, low-rank solution directly.
  arXiv  Detail & Related papers  (2026-02-11T16:19:58Z)
• LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis [33.708800231646606]
  We establish a theoretical framework for data-aware LoRA.<n>We develop an efficient algorithm, LoRA-DA, which estimates the terms in the optimization problem from a small set of target domain samples.<n>Additional studies show faster, more stable convergence, robustness across ranks, and only a small overhead for LoRA-DA.
  arXiv  Detail & Related papers  (2025-10-28T15:55:36Z)
• Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes [9.4848188271008]
  Low-Rank Adaptation (LoRA) has proven effective in reducing computational costs while maintaining performance comparable to fully fine-tuned foundation models.<n>Current adaptive LoRA methods attempt to overcome this limitation by dynamically expanding or selectively allocating ranks.<n>We introduce Stable Rank-Guided Low-Rank Adaptation (SR-LoRA), a novel framework that utilizes the stable rank of pre-trained weight matrices as a natural prior for layer-wise rank allocation.
  arXiv  Detail & Related papers  (2025-06-30T23:54:23Z)
• SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization [2.594346658179846]
  Low-Rank Adaptation (LoRA) constrains updates to a fixed low-rank subspace.<n>We introduce Subspace Recomposition in Low-Rank Adaptation (SRLoRA) via importance-based fusion and reinitialization.<n> SRLoRA consistently achieves faster convergence and improved accuracy over standard LoRA.
  arXiv  Detail & Related papers  (2025-05-18T14:12:40Z)
• ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning [6.657174308208715]
  ElaLoRA is an adaptive low-rank adaptation framework that dynamically prunes and expands ranks based on gradient-derived importance scores. ElaLoRA consistently outperforms existing PEFT methods across different parameter budgets. By introducing a principled and adaptive rank allocation mechanism, ElaLoRA offers a scalable and efficient fine-tuning solution.
  arXiv  Detail & Related papers  (2025-03-31T21:58:25Z)
• BeamLoRA: Beam-Constraint Low-Rank Adaptation [51.52097743781401]
  Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods. We propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution.
  arXiv  Detail & Related papers  (2025-02-19T10:33:22Z)
• S-LoRA: Scalable Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising approach to harnessing the power of pre-trained models for sequential tasks.<n>We propose a Scalable Low-Rank Adaptation (S-LoRA) method for CL (in particular class incremental learning), which incrementally decouples the learning of the direction and magnitude of LoRA parameters.<n>Our theoretical and empirical analysis demonstrates that S-LoRA tends to follow a low-loss trajectory that converges to an overlapped low-loss region, resulting in an excellent stability-plasticity trade-off in CL.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• 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)
• LoRA-Pro: Are Low-Rank Adapters Properly Optimized? [121.0693322732454]
  Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models. Despite its computational efficiency, LoRA still yields inferior performance compared to full fine-tuning. We introduce LoRA-Pro, a method that enhances LoRA's performance by strategically adjusting the gradients of low-rank matrices.
  arXiv  Detail & Related papers  (2024-07-25T17:57:12Z)
• Enhancing Parameter Efficiency and Generalization in Large-Scale Models: A Regularized and Masked Low-Rank Adaptation Approach [10.980433187379868]
  Low-Rank Adaptation (LoRA) has been developed to reduce resource consumption while maintaining satisfactory fine-tuning results. This paper investigates the intrinsic dimension of the matrix updates approximated by the LoRA method and reveals the performance benefits of increasing this intrinsic dimension.
  arXiv  Detail & Related papers  (2024-07-16T15:26:31Z)
• ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models [8.251547772610301]
  We extend the methodology of low-rank adaptation (LoRA) to an innovative approach we call allocating low-rank adaptation (ALoRA) First, we propose a novel method, AB-LoRA, that can effectively estimate the importance score of each LoRA rank. Second, guided by AB-LoRA, we gradually prune abundant and negatively impacting LoRA ranks and allocate the pruned LoRA budgets to important Transformer modules needing higher ranks.
  arXiv  Detail & Related papers  (2024-03-24T15:09:55Z)
• PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA [45.38491644250814]
  Partially Rotation-enhanced Low-Rank Adaptation (PRoLoRA) is an intra-layer sharing mechanism. PRoLoRA retains its advantages, and effectively circumvents the drawbacks of peer parameter-sharing methods. Empirical experiments demonstrate the remarkably higher parameter efficiency of PRoLoRA.
  arXiv  Detail & Related papers  (2024-02-24T13:39:05Z)
• PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation [65.268245109828]
  We introduce PRILoRA, which linearly allocates a different rank for each layer, in an increasing manner, and performs pruning throughout the training process. We validate the effectiveness of PRILoRA through extensive experiments on eight GLUE benchmarks, setting a new state of the art.
  arXiv  Detail & Related papers  (2024-01-20T20:25:17Z)
• Sparse Low-rank Adaptation of Pre-trained Language Models [79.74094517030035]
  We introduce sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process. Our approach strengthens the representation power of LoRA by initializing it with a higher rank, while efficiently taming a temporarily increased number of parameters. Our experimental results demonstrate that SoRA can outperform other baselines even with 70% retained parameters and 70% training time.
  arXiv  Detail & Related papers  (2023-11-20T11:56:25Z)

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.