Memory-Efficient Fine-Tuning via Low-Rank Activation Compression

• URL: http://arxiv.org/abs/2509.23472v1
• Date: Sat, 27 Sep 2025 19:48:32 GMT
• Title: Memory-Efficient Fine-Tuning via Low-Rank Activation Compression
• Authors: Jiang-Xin Shi, Wen-Da Wei, Jin-Fei Qi, Xuanyu Chen, Tong Wei, Yu-Feng Li,
• Abstract summary: Low-Rank Activation Compression (LoRAct) is a memory-efficient fine-tuning approach.<n>LoRAct reduces activation memory by approximately 80% in comparison with the widely adopted LoRA method.
• Score: 16.44044624606008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The parameter-efficient fine-tuning paradigm has garnered significant attention with the advancement of foundation models. Although numerous methods have been proposed to reduce the number of trainable parameters, their substantial memory overhead remains a critical bottleneck that hinders practical deployment. In this paper, we observe that model activations constitute a major source of memory consumption, especially under large batch sizes and long context lengths; however, the rank of the activations remains consistently low. Motivated by this insight, we propose a memory-efficient fine-tuning approach Low-Rank Activation Compression (LoRAct). Unlike prior work, LoRAct provides a more flexible and versatile compressing strategy that can be applied online during the forward pass without the need for any calibration data. Moreover, LoRAct incorporates a novel sampling-based orthogonal decomposition algorithm specifically designed for low-rank matrices, offering improved computational efficiency and a tighter error bound compared to the widely used RSVD. Experiments on both vision and language tasks demonstrate the effectiveness of LoRAct. Notably, LoRAct further reduces activation memory by approximately 80% in comparison with the widely adopted LoRA method, while maintaining competitive performance. The source code is available at https://github.com/shijxcs/meft.

Related papers

• Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>In this work, we address the gap between training with full steps with low-rank projections (SVDLoRA) and LoRA fine-tuning.<n>We propose LoRSum, a memory-efficient subroutine that closes this gap for gradient descent.
  arXiv  Detail & Related papers  (2026-02-18T13:41:41Z)
• Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog [72.4168434368873]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources.<n>We propose a gradual compacting method that divides the compression process into multiple fine-grained iterations.<n>This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss.
  arXiv  Detail & Related papers  (2026-02-04T06:56:52Z)
• TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching [82.13572707265513]
  Fine tuning has been regarded as a de facto approach for adapting large language models to downstream tasks.<n>We propose TokenSeek, a universal plugin solution for various transformer-based models through instance-aware token seeking and ditching.
  arXiv  Detail & Related papers  (2026-01-27T15:58:36Z)
• CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure [8.92064131103945]
  Cross-layer Low-Rank residual Network (CR-Net) is an innovative framework inspired by our discovery that inter-layer activation residuals possess low-rank properties.<n>CR-Net consistently outperforms state-of-the-art low-rank frameworks while requiring fewer computational resources and less memory.
  arXiv  Detail & Related papers  (2025-09-23T13:43:02Z)
• Low-rank Momentum Factorization for Memory Efficient Training [13.464518325870444]
  Momentum Factorized (MoFaSGD) maintains a dynamically updated low-rank SVD representation of the first-order momentum.<n>We demonstrate MoFaSGD's effectiveness on large language model benchmarks, achieving a competitive trade-off between memory reduction (e.g. LoRA) and performance.
  arXiv  Detail & Related papers  (2025-07-10T18:04:52Z)
• LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model [21.98687961440789]
  Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity.<n>Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms.<n>We introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs.
  arXiv  Detail & Related papers  (2025-01-15T05:07:06Z)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape [52.98187034726091]
  We introduce Flat-LoRA, which aims to identify a low-rank adaptation situated in a flat region of the full parameter space.<n>We show that Flat-LoRA improves both in-domain and out-of-domain generalization.
  arXiv  Detail & Related papers  (2024-09-22T11:24:10Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation [29.139579820699495]
  This work strives to reduce memory overhead in fine-tuning from perspectives of activation function and layer normalization. We apply our Approx-BP theory to backpropagation training and derive memory-efficient alternatives of GELU and SiLU activation functions. In addition, we introduce a Memory-Sharing Backpropagation strategy, which enables the activation memory to be shared by two adjacent layers.
  arXiv  Detail & Related papers  (2024-06-24T03:09:15Z)
• Mesa: A Memory-saving Training Framework for Transformers [58.78933015299703]
  We present Mesa, a memory-saving training framework for Transformers. Mesa uses exact activations during forward pass while storing a low-precision version of activations to reduce memory consumption during training. Experiments on ImageNet, CIFAR-100 and ADE20K demonstrate that Mesa can reduce half of the memory footprints during training.
  arXiv  Detail & Related papers  (2021-11-22T11:23:01Z)

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.