Fine-Tuning Linear Layers Only Is a Simple yet Effective Way for Task Arithmetic

• URL: http://arxiv.org/abs/2407.07089v1
• Date: Tue, 9 Jul 2024 17:59:17 GMT
• Title: Fine-Tuning Linear Layers Only Is a Simple yet Effective Way for Task Arithmetic
• Authors: Ruochen Jin, Bojian Hou, Jiancong Xiao, Weijie Su, Li Shen,
• Abstract summary: We propose a method that only fine-tunes linear layers, which improves weight disentanglement and efficiency simultaneously. Our study reveals that only fine-tuning the linear layers in the attention modules makes the whole model occur in a linear regime. In particular, we find that the representation model plays an important role in improving weight disentanglement whereas the task-specific models such as the classification heads can degenerate the weight disentanglement performance.
• Score: 11.142414096809734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space, by adding the fine-tuned weights of different tasks. The performance has been further improved by a linear property which is illustrated by weight disentanglement. Yet, conventional linearization methods (e.g., NTK linearization) not only double the time and training cost but also have a disadvantage on single-task performance. We propose a simple yet effective and efficient method that only fine-tunes linear layers, which improves weight disentanglement and efficiency simultaneously. Specifically, our study reveals that only fine-tuning the linear layers in the attention modules makes the whole model occur in a linear regime, significantly improving weight disentanglement. To further understand how our method improves the disentanglement of task arithmetic, we present a comprehensive study of task arithmetic by differentiating the role of representation model and task-specific model. In particular, we find that the representation model plays an important role in improving weight disentanglement whereas the task-specific models such as the classification heads can degenerate the weight disentanglement performance. Overall, our work uncovers novel insights into the fundamental mechanisms of task arithmetic and offers a more reliable and effective approach to editing pre-trained models.

Related papers

• NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models [26.808251361020066]
  Fine-tuning pre-trained models is resource-intensive and laborious. One widely adopted PEFT technique, Low-Rank Adaptation (LoRA), freezes the pre-trained model weights. NEAT introduces a lightweight neural network that takes pre-trained weights as input and learns a nonlinear transformation to approximate cumulative weight updates.
  arXiv  Detail & Related papers  (2024-10-02T17:29:23Z)
• Model-Based Transfer Learning for Contextual Reinforcement Learning [5.5597941107270215]
  We show how to systematically select good tasks to train, maximizing overall performance across a range of tasks. Key idea behind our approach is to explicitly model the performance loss incurred by transferring a trained model. We experimentally validate our methods using urban traffic and standard control benchmarks.
  arXiv  Detail & Related papers  (2024-08-08T14:46:01Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? [92.90857135952231]
  Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities. We study ICL in one of its simplest setups: pretraining a linearly parameterized single-layer linear attention model for linear regression.
  arXiv  Detail & Related papers  (2023-10-12T15:01:43Z)
• Parameter Efficient Multi-task Model Fusion with Partial Linearization [97.23530944186078]
  We propose a novel method to improve multi-task fusion for parameter-efficient fine-tuning techniques. Our approach partially linearizes only the adapter modules and applies task arithmetic over the linearized adapters. We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model.
  arXiv  Detail & Related papers  (2023-10-07T08:55:54Z)
• Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models [96.9373147383119]
  We show that weight disentanglement is the crucial factor that makes task arithmetic effective. We show that fine-tuning models in their tangent space by linearizing them amplifies weight disentanglement. This leads to substantial performance improvements across task arithmetic benchmarks and diverse models.
  arXiv  Detail & Related papers  (2023-05-22T08:39:25Z)
• Towards Compute-Optimal Transfer Learning [82.88829463290041]
  We argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.
  arXiv  Detail & Related papers  (2023-04-25T21:49:09Z)
• Scalable Weight Reparametrization for Efficient Transfer Learning [10.265713480189486]
  Efficient transfer learning involves utilizing a pre-trained model trained on a larger dataset and repurposing it for downstream tasks. Previous works have led to an increase in updated parameters and task-specific modules, resulting in more computations, especially for tiny models. We suggest learning a policy network that can decide where to reparametrize the pre-trained model, while adhering to a given constraint for the number of updated parameters.
  arXiv  Detail & Related papers  (2023-02-26T23:19:11Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)

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.