Implementation of paper "Towards a Unified View of Parameter-Efficient Transfer Learning"

Overview

A Unified Framework for Parameter-Efficient Transfer Learning

This is the official implementation of the paper:

Towards a Unified View of Parameter-Efficient Transfer Learning
Junxian He*, Chunting Zhou*, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig
Preprint 2021

Parameter-efficient transfer learning (PETL) methods only tune a small number of (extra) parameters to adapt large pretrained models into downstream tasks. This paper reveals the connection among existing PETL methods such as adapters, prefix tuning, and LoRA, and proposes a unified framework to interpret their designs. This unified framework is able to instantiate existing approaches by varying values along several defined design dimensions, which also provides principled guidance to design new PETL methods. In this repo as well as in the paper, we include examples of how we easily derive new state-of-the-art PETL methods from the unified framework.

intro

Dependencies

This repo is a fork of the huggingface transformers repo (forked on June 23, 2021), and the code is tested on PyTorch 1.9.0. Please follow the instructions below to install dependencies after you set up PyTorch:

git clone [email protected]:jxhe/MAM-adapter.git
cd MAM-adapter

# install transformers from this repo
pip install -e .

# install other requirements
pip install datasets==1.11.0

# used to compute BLEU score for en-ro translation
git clone [email protected]:moses-smt/mosesdecoder.git

Usage

MAM-Adapter

Run the following command to reproduce the MAM-Adapter results in the paper on the XSum, en-ro translation, MNLI, or SST2 datasets:

bash exps/run_{xsum|en_ro|glue}.sh

We ran all the experiments with one A6000 or A100 GPU that has >=40GB GPU memory -- if your GPU does not have a large memory, you may need to reduce the bsz (max_tokens_per_batch for en-ro) and increase the gradient_steps values in the scripts to match our effective batch size. You may train with multiple GPUs easily with python -m torch.distributed.launch --nproc_per_node {num_gpus} to enable data parallelism.

Training time: in our experiments that use one GPU, XSum takes 24 hours w/ A100 or 50 hours w/ A6000, en-ro takes 20 hours w/ A6000, SST2 takes 2 hours, and MNLI takes 10 hours.

Advanced Usage for Other PETL Variants

As the paper shows, our unified framework instantiates different PETL variants easily by varying along the design dimensions. You can modify the script to train other PETL variants as we studied in the paper, we include some examples in run_xsum.sh, which can be directly applied to the other scripts as well:

# ----- MAM adapter -----
attn_mode="prefix"
attn_option="concat"
attn_composition="add"
attn_bn=30  # attn bottleneck dim

ffn_mode="adapter"
ffn_option="parallel"
ffn_adapter_layernorm_option="none"
ffn_adapter_init_option="lora"
ffn_adapter_scalar="4"
ffn_bn=512 # ffn bottleneck dim

# ----- prefix tuning baseline ----- 
# attn_mode="prefix"
# attn_option="concat"
# attn_composition="add"
# attn_bn=200  # attn bottleneck dim

# ffn_mode="none"
# ffn_option="parallel"
# ffn_adapter_layernorm_option="none"
# ffn_adapter_init_option="lora"
# ffn_adapter_scalar="4"
# ffn_bn=512 # ffn bottleneck dim

# ----- Houlsby Adapter ----- 
# attn_mode="adapter"
# attn_option="sequential"
# attn_composition="add"
# attn_bn=200  # attn bottleneck dim

# ffn_mode="adapter"
# ffn_option="sequential"
# ffn_adapter_layernorm_option="none"
# ffn_adapter_init_option="bert"
# ffn_adapter_scalar="1"
# ffn_bn=200 # ffn bottleneck dim

# ----- FFN Scaled Parallel Adapter ----- 
# attn_mode="None"
# attn_option="parallel"
# attn_composition="add"
# attn_bn=200  # attn bottleneck dim

# ffn_mode="adapter"
# ffn_option="parallel"
# ffn_adapter_layernorm_option="none"
# ffn_adapter_init_option="lora"
# ffn_adapter_scalar="4"
# ffn_bn=512 # ffn bottleneck dim

There are more variations than what is shown above. Please see a complete explanation of these arguments here in petl/options.py. The results of all the variants reported in the paper could be reproduced by changing these values in the scripts.

Citation

@article{he2021towards,
  title={Towards a Unified View of Parameter-Efficient Transfer Learning},
  author={He, Junxian and Zhou, Chunting and Ma, Xuezhe and Berg-Kirkpatrick, Taylor and Neubig, Graham},
  journal={arXiv preprint arXiv:2110.04366},
  year={2021}
}
Owner
Junxian He
NLP/ML PhD student at CMU
Junxian He
TJU Deep Learning & Neural Network

Deep_Learning & Neural_Network_Lab 实验环境 Python 3.9 Anaconda3(官网下载或清华镜像都行) PyTorch 1.10.1(安装代码如下) conda install pytorch torchvision torchaudio cudatool

St3ve Lee 1 Jan 19, 2022
Memory Defense: More Robust Classificationvia a Memory-Masking Autoencoder

Memory Defense: More Robust Classificationvia a Memory-Masking Autoencoder Authors: - Eashan Adhikarla - Dan Luo - Dr. Brian D. Davison Abstract Many

Eashan Adhikarla 4 Dec 25, 2022
Instant Real-Time Example-Based Style Transfer to Facial Videos

FaceBlit: Instant Real-Time Example-Based Style Transfer to Facial Videos The official implementation of FaceBlit: Instant Real-Time Example-Based Sty

Aneta Texler 131 Dec 19, 2022
code for our BMVC 2021 paper "HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification"

HCV_IIRC code for our BMVC 2021 paper HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification by Kai Wang, Xialei Li

kai wang 13 Oct 03, 2022
clustimage is a python package for unsupervised clustering of images.

clustimage The aim of clustimage is to detect natural groups or clusters of images. Image recognition is a computer vision task for identifying and ve

Erdogan Taskesen 52 Jan 02, 2023
This repository introduces a short project about Transfer Learning for Classification of MRI Images.

Transfer Learning for MRI Images Classification This repository introduces a short project made during my stay at Neuromatch Summer School 2021. This

Oscar Guarnizo 3 Nov 15, 2022
pytorch bert intent classification and slot filling

pytorch_bert_intent_classification_and_slot_filling 基于pytorch的中文意图识别和槽位填充 说明 基本思路就是:分类+序列标注(命名实体识别)同时训练。 使用的预训练模型:hugging face上的chinese-bert-wwm-ext 依

西西嘛呦 33 Dec 15, 2022
nn_builder lets you build neural networks with less boilerplate code

nn_builder lets you build neural networks with less boilerplate code. You specify the type of network you want and it builds it. Install pip install n

Petros Christodoulou 157 Nov 20, 2022
Time Dependent DFT in Tamm-Dancoff Approximation

Density Function Theory Program - kspy-tddft(tda) This is an implementation of Time-Dependent Density Functional Theory(TDDFT) using the Tamm-Dancoff

Peter Borthwick 2 Nov 17, 2022
A repository for storing njxzc final exam review material

文档地址,请戳我 👈 👈 👈 ☀️ 1.Reason 大三上期末复习软件工程的时候,发现其他高校在GitHub上开源了他们学校的期末试题,我很受触动。期末

GuJiakai 2 Jan 18, 2022
Experiment about Deep Person Re-identification with EfficientNet-v2

We evaluated the baseline with Resnet50 and Efficienet-v2 without using pretrained models. Also Resnet50-IBN-A and Efficientnet-v2 using pretrained on ImageNet. We used two datasets: Market-1501 and

lan.nguyen2k 77 Jan 03, 2023
Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network.

Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network

111 Dec 27, 2022
Img-process-manual - Utilize Python Numpy and Matplotlib to realize OpenCV baisc image processing function

Img-process-manual - Opencv Library basic graphic processing algorithm coding reproduction based on Numpy and Matplotlib library

Jack_Shaw 2 Dec 12, 2022
A collection of Google research projects related to Federated Learning and Federated Analytics.

Federated Research Federated Research is a collection of research projects related to Federated Learning and Federated Analytics. Federated learning i

Google Research 483 Jan 05, 2023
Reimplementation of Learning Mesh-based Simulation With Graph Networks

Pytorch Implementation of Learning Mesh-based Simulation With Graph Networks This is the unofficial implementation of the approach described in the pa

Jingwei Xu 33 Dec 14, 2022
Pytorch Implementations of large number classical backbone CNNs, data enhancement, torch loss, attention, visualization and some common algorithms.

Torch-template-for-deep-learning Pytorch implementations of some **classical backbone CNNs, data enhancement, torch loss, attention, visualization and

Li Shengyan 270 Dec 31, 2022
Pytorch implementation of OCNet series and SegFix.

openseg.pytorch News 2021/09/14 MMSegmentation has supported our ISANet and refer to ISANet for more details. 2021/08/13 We have released the implemen

openseg-group 1.1k Dec 23, 2022
[CVPR 2021] Official PyTorch Implementation for "Iterative Filter Adaptive Network for Single Image Defocus Deblurring"

IFAN: Iterative Filter Adaptive Network for Single Image Defocus Deblurring Checkout for the demo (GUI/Google Colab)! The GUI version might occasional

Junyong Lee 173 Dec 30, 2022
PyTorch implementation of "Learn to Dance with AIST++: Music Conditioned 3D Dance Generation."

Learn to Dance with AIST++: Music Conditioned 3D Dance Generation. Installation pip install -r requirements.txt Prepare Dataset bash data/scripts/pre

Zj Li 8 Sep 07, 2021
CondenseNet: Light weighted CNN for mobile devices

CondenseNets This repository contains the code (in PyTorch) for "CondenseNet: An Efficient DenseNet using Learned Group Convolutions" paper by Gao Hua

Shichen Liu 690 Nov 30, 2022