GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models

• URL: http://arxiv.org/abs/2507.04455v1
• Date: Sun, 06 Jul 2025 16:27:27 GMT
• Title: GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
• Authors: Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Wei Wang, Jianke Zhu,
• Abstract summary: This paper introduces a novel OT approach based on gradient-preserving compression, named GradOT.<n>By analyzing the OT problem through the lens of optimization, we propose a method that selectively applies compression techniques such as rank compression and channel pruning, preserving the gradients of fine-tuned adapters while ensuring privacy.
• Score: 15.489070604001466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data owners. One promising solution, called offsite-tuning (OT), is proposed to address these challenges, where a weaker emulator is compressed from the original model and further fine-tuned with adapter to enhance privacy. However, the existing OT-based methods require high computational costs and lack theoretical analysis. This paper introduces a novel OT approach based on gradient-preserving compression, named GradOT. By analyzing the OT problem through the lens of optimization, we propose a method that selectively applies compression techniques such as rank compression and channel pruning, preserving the gradients of fine-tuned adapters while ensuring privacy. Extensive experiments demonstrate that our approach surpasses existing OT methods, both in terms of privacy protection and model performance. Our method provides a theoretical foundation for OT and offers a practical, training-free solution for offsite-tuning of large-scale LLMs.

Related papers

• Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation [67.80294336559574]
  Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios.<n>We propose a novel pipeline, Orthogonal Projection Subspace to aggregate online Prior-knowledge, dubbed OoPk.
  arXiv  Detail & Related papers  (2025-06-23T18:17:39Z)
• Sequential Policy Gradient for Adaptive Hyperparameter Optimization [6.031164586412059]
  We propose Sequential Policy Gradient modeling (SPG), a novel trajectory generation paradigm for lightweight online hyperparameter optimization.<n>SPG extends the base model with temporary modules, enabling it to generate state-action (padded) trajectories in a single forward pass.<n>Our experiments demonstrate that models gain performance when retrained with SPG on their original datasets and also outperform standard transfer fine-tuning.
  arXiv  Detail & Related papers  (2025-06-18T01:21:39Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• Sparse Gradient Compression for Fine-Tuning Large Language Models [58.44973963468691]
  Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models.<n>High memory costs associated with fine-tuning remain a significant challenge, especially as models increase in size.<n>We propose sparse compression gradient (SGC) to address these limitations.
  arXiv  Detail & Related papers  (2025-02-01T04:18:28Z)
• Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models [2.3281513013731145]
  Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. Differential Privacy (DP) offers a solution to mitigate these risks, but introduces significant computational and performance trade-offs. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage.
  arXiv  Detail & Related papers  (2024-11-24T13:17:36Z)
• Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training [10.229653770070202]
  Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data. We present a kernel-based estimator for this divergence, circumventing the need for adversarial training.
  arXiv  Detail & Related papers  (2024-10-25T19:32:58Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning [95.64041188351393]
  This paper endeavors to solve both the challenges of limited resources and personalization. We propose a method named ZOOPFL that uses Zeroth-Order Optimization for Personalized Federated Learning. To reduce the computation costs and enhance personalization, we propose input surgery to incorporate an auto-encoder with low-dimensional and client-specific embeddings.
  arXiv  Detail & Related papers  (2023-10-08T12:26:13Z)
• Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation [2.741266294612776]
  Low-rank model compression is a widely used technique for reducing the computational load when training machine learning models. Existing compression techniques are not directly applicable to efficient over-the-air (OTA) aggregation in federated learning systems. We propose a novel manifold optimization formulation for low-rank model compression in FL that does not relax the low-rank constraint.
  arXiv  Detail & Related papers  (2023-06-04T18:32:50Z)
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation [120.69747175899421]
  Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. We propose a computationally-efficient dual form of the robust OT optimization that is amenable to modern deep learning applications. Our approach can train state-of-the-art GAN models on noisy datasets corrupted with outlier distributions.
  arXiv  Detail & Related papers  (2020-10-12T17:13:40Z)

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.