PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation
- URL: http://arxiv.org/abs/2403.09192v4
- Date: Thu, 18 Jul 2024 09:25:59 GMT
- Title: PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation
- Authors: Yizhe Xiong, Hui Chen, Tianxiang Hao, Zijia Lin, Jungong Han, Yuesong Zhang, Guoxin Wang, Yongjun Bao, Guiguang Ding,
- Abstract summary: We propose a novel Parallel Yielding Re-Activation (PYRA) method for training-inference efficient task adaptation.
PYRA outperforms all competing methods under both low compression rate and high compression rate.
- Score: 61.57833648734164
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, the scale of transformers has grown rapidly, which introduces considerable challenges in terms of training overhead and inference efficiency in the scope of task adaptation. Existing works, namely Parameter-Efficient Fine-Tuning (PEFT) and model compression, have separately investigated the challenges. However, PEFT cannot guarantee the inference efficiency of the original backbone, especially for large-scale models. Model compression requires significant training costs for structure searching and re-training. Consequently, a simple combination of them cannot guarantee accomplishing both training efficiency and inference efficiency with minimal costs. In this paper, we propose a novel Parallel Yielding Re-Activation (PYRA) method for such a challenge of training-inference efficient task adaptation. PYRA first utilizes parallel yielding adaptive weights to comprehensively perceive the data distribution in downstream tasks. A re-activation strategy for token modulation is then applied for tokens to be merged, leading to calibrated token features. Extensive experiments demonstrate that PYRA outperforms all competing methods under both low compression rate and high compression rate, demonstrating its effectiveness and superiority in maintaining both training efficiency and inference efficiency for large-scale foundation models. Our code is available at https://github.com/THU-MIG/PYRA.
Related papers
- EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [76.72669153805018]
EoRA consistently outperforms previous methods in compensating errors for compressed LLaMA2/3 models on various tasks.
EoRA offers a scalable, training-free solution to compensate for compression errors.
arXiv Detail & Related papers (2024-10-28T17:59:03Z) - Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks.
Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum.
We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
arXiv Detail & Related papers (2024-10-25T17:07:13Z) - Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition [22.615830919860777]
This paper presents an efficient visual recognition paradigm, called Dynamic Adapter (Dyn-Adapter)
We devise a dynamic architecture with balanced early heads for multi-level feature extraction, along with adaptive training strategy.
We reduce FLOPs during inference by 50%, while maintaining or even yielding higher recognition accuracy.
arXiv Detail & Related papers (2024-07-19T13:33:38Z) - Parameter-Efficient Fine-Tuning With Adapters [5.948206235442328]
This research introduces a novel adaptation method utilizing the UniPELT framework as a base.
Our method employs adapters, which enable efficient transfer of pretrained models to new tasks with minimal retraining of the base model parameters.
arXiv Detail & Related papers (2024-05-09T01:40:38Z) - DiJiang: Efficient Large Language Models through Compact Kernelization [30.24187657746638]
We present a novel Frequency Domain Kernelization approach that enables the transformation of a pre-trained vanilla Transformer into a linear complexity model with little training costs.
Experiments demonstrate that the proposed method achieves comparable performance to the original Transformer, but with significantly reduced training costs and much faster inference speeds.
arXiv Detail & Related papers (2024-03-29T02:32:15Z) - TAIL: Task-specific Adapters for Imitation Learning with Large
Pretrained Models [32.83440439290383]
We introduce TAIL (Task-specific Adapters for Learning), a framework for efficient adaptation to new control tasks.
Inspired by recent advancements in parameter-efficient fine-tuning in language domains, we explore efficient fine-tuning techniques.
Our experiments in large-scale language-conditioned manipulation tasks suggest that TAIL with LoRA can achieve the best post-adaptation performance.
arXiv Detail & Related papers (2023-10-09T17:49:50Z) - Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than
In-Context Learning [81.3514358542452]
Few-shot in-context learning (ICL) incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
parameter-efficient fine-tuning offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task.
In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs.
arXiv Detail & Related papers (2022-05-11T17:10:41Z) - Online Convolutional Re-parameterization [51.97831675242173]
We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution.
Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x.
We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
arXiv Detail & Related papers (2022-04-02T09:50:19Z) - Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples.
We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment.
We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
arXiv Detail & Related papers (2022-03-23T06:24:31Z)
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.