Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Overview

🌀 WARP: Word-level Adversarial ReProgramming

This repository contains code for ACL'2021 Paper WARP: Word-level Adversarial ReProgramming.

WARP adds a few trainable embeddings around the input, which causes the masked language model to predict the sentiment of the sentence in the SST-2 task.

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific layers on top of the language model.

In this paper, we present an alternative approach based on adversarial reprogramming, which extends earlier work on automatic prompt generation. Adversarial reprogramming attempts to learn task-specific word embeddings that, when concatenated to the input text, instruct the language model to solve the specified task.

Using up to 25K trainable parameters per task, this approach outperforms all existing methods that use up to 25M trainable parameters on the public leaderboard of the GLUE benchmark. Our method, initialized with task-specific human-readable prompts, also works in a few-shot setting, outperforming GPT-3 on two SuperGLUE tasks after training on just 32 samples.

Few-Shot Results

Set Model CB RTE
F1 Acc. Acc.
dev
GPT-3 Small 26.1 42.9 52.3
GPT-3 Med 40.4 58.9 48.4
GPT-3 57.2 82.1 72.9
PET (ALBERT) 59.4 85.1 69.8
iPET (ALBERT) 92.4 92.9 74.0
WARPinit (ALBERT) 84.0 87.5 71.8
test
GPT-3 52.0 75.6 69.0
PET (ALBERT) 60.2 87.2 67.2
iPET (ALBERT) 79.9 88.8 70.8
WARPinit (ALBERT) 70.2 82.4 69.1
Results on SuperGLUE benchmark. The results for the test set are obtained from SuperGLUE evaluation server. We only show systems performing in a similar few-shot training setup using 32 examples.

Setup

The code requires YerevaNN's internal version of allennlp

git clone https://github.com/YerevaNN/allennlp
git checkout warp
pip install .

Training

Linear Probing

for DATASET in 'cola' 'sst2' 'mrpc' 'qqp' 'stsb' 'mnli' 'rte' 'wnli' 'qnli'
do
    export HPARAMS='{
        "dataset": "'$DATASET'",
        "lr": 0.0001,
        "num_epochs": 20,
        "prompts": [],
        "reorder_optimized": false,
        "max_batch_size": 8,
        "max_tokens_sq": 262144, "on_logits":  false, "pooling_index":  null, "seed":  1}'
    python -m allennlp train \
    -s .aim/baseline-linear-${DATASET} configs/warp.jsonnet
done

WARP_0

"], "reorder_optimized": true, "max_batch_size": 8, "max_tokens_sq": 262144, "on_logits": "pre_decoder_layer_norm", "pooling_index": 1, "seed": 1 }' python -m allennlp train \ -s .aim/baseline-warp_0-${DATASET} configs/warp.jsonnet done ">
for DATASET in 'cola' 'sst2' 'mrpc' 'qqp' 'stsb' 'mnli' 'rte' 'wnli' 'qnli'
do
    export HPARAMS='{
        "dataset": "'$DATASET'",
        "lr": 0.0001,
        "num_epochs": 20,
        "prompts": [null, "
   
    "],
   
        "reorder_optimized": true,
        "max_batch_size": 8,
        "max_tokens_sq": 262144,
        "on_logits": "pre_decoder_layer_norm",
        "pooling_index": 1,
        "seed": 1
    }'
    python -m allennlp train \
    -s .aim/baseline-warp_0-${DATASET} configs/warp.jsonnet
done

Training WARP

", "prompts":[-10,-11,-12,-13,-14,null,-15,-16,-17,-18,-19," ",-20,-21,-22,-23,-24,null,-25,-26,-27,-28,-29], "seed":1, "transformer_model":"roberta-large" }' python -m allennlp train \ -s .aim/t-${DATASET} configs/warp.jsonnet ">
export DATASET="rte"
export HPARAMS='{
    "benchmark":"super_glue",
    "classifier_init":null,
    "dataset":"'$DATASET'",
    "ensure_whitespace_between":false,
    "lr":0.001,
    "max_batch_size":8,
    "max_tokens_sq":262144,
    "num_epochs":30,
    "prompt_better_init":"
    
     ",
    
    "prompts":[-10,-11,-12,-13,-14,null,-15,-16,-17,-18,-19,"
    
     ",-20,-21,-22,-23,-24,null,-25,-26,-27,-28,-29],
    
    "seed":1,
    "transformer_model":"roberta-large"
}'
python -m allennlp train \
-s .aim/t-${DATASET} configs/warp.jsonnet

WARP_init

Few-Shot Experiments

", [-20, ","], null, [-29, "!"],-30,-31], "seed":3, "str_cut_frac":0, "transformer_model":"albert-xxlarge-v2", "validation_metric": null }' python -m allennlp train \ -s .aim/t-${DATASET}-`date +%s` configs/warp.jsonnet ">
export HPARAMS='{
    "benchmark":"super_glue",
    "classifier_init": {
        "entailment": " yes",
        "not_entailment": " instead"
    },
    "dataset":"few_rte",
    "eval_mode":false,
    "lr":0.001,
    "max_batch_size":2,
    "max_tokens_sq":131072,
    "num_epochs":100,
    "num_gradient_accumulation_steps":2,
    "prompt_better_init": "[PAD]",
    "prompts":[-10,-11,[-14,"\""],null,[-15,"\""],  [-16, "?"], "
   
    ", [-20, ","], null, [-29, "!"],-30,-31],
   
    "seed":3,
    "str_cut_frac":0,
    "transformer_model":"albert-xxlarge-v2",
    "validation_metric": null
}'
python -m allennlp train \
-s .aim/t-${DATASET}-`date +%s` configs/warp.jsonnet
",[-20,","],null,[-29,"!"],-30,-31], "seed":1, "str_cut_frac":0.06, "transformer_model":"albert-xxlarge-v2", "validation_metric":"+training_val_metric" }' python -m allennlp train \ -s .aim/t-${DATASET}-`date +%s` configs/warp.jsonnet ">
export HPARAMS='{
   "benchmark":"super_glue",
   "classifier_init":{
      "entailment":" yes",
      "not_entailment":" instead"
   },
   "dataset":"few_rte",
   "grad_norm":1,
   "lr":0.001,
   "max_batch_size":2,
   "max_tokens_sq":131072,
   "num_epochs":30,
   "num_gradient_accumulation_steps":2,
   "prompt_better_init":"[PAD]",
   "prompts":[-10,-11,[-14,"\""],null,[-15,"\""],[-16,"?"],"
   
    ",[-20,","],null,[-29,"!"],-30,-31],
   
   "seed":1,
   "str_cut_frac":0.06,
   "transformer_model":"albert-xxlarge-v2",
   "validation_metric":"+training_val_metric"
}'
python -m allennlp train \
-s .aim/t-${DATASET}-`date +%s` configs/warp.jsonnet

Evaluation

python -m allennlp predict \
  --silent --use-dataset-reader --cuda-device 0 \
  --batch-size 50 \
  --predictor glue --output-file v0.1/AX.tsv /data/arp/.aim/H-93ae5ae9 ax/test
python -m allennlp predict \
  --silent --use-dataset-reader --cuda-device 0 \
  --batch-size 50 \
  --predictor glue --output-file v0.1/MNLI-m.tsv /data/arp/.aim/H-93ae5ae9 test_matched

Citation

If you want to refer to our work use this bibTeX:

@inproceedings{hambardzumyan-etal-2021-warp,
    title = "{WARP}: {W}ord-level {A}dversarial {R}e{P}rogramming",
    author = "Hambardzumyan, Karen  and
      Khachatrian, Hrant  and
      May, Jonathan",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.381",
    doi = "10.18653/v1/2021.acl-long.381",
    pages = "4921--4933"
}
Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"

GEN-VLKT Code for our CVPR 2022 paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection". Contributed by Yue Lia

Yue Liao 47 Dec 04, 2022
Creating Artificial Life with Reinforcement Learning

Although Evolutionary Algorithms have shown to result in interesting behavior, they focus on learning across generations whereas behavior could also be learned during ones lifetime.

Maarten Grootendorst 49 Dec 21, 2022
Tiny Kinetics-400 for test

Kinetics-400迷你数据集 English | 简体中文 该数据集旨在解决的问题:参照Kinetics-400数据格式,训练基于自己数据的视频理解模型。 数据集介绍 Kinetics-400是视频领域benchmark常用数据集,详细介绍可以参考其官方网站Kinetics。整个数据集包含40

38 Jan 06, 2023
Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

Segformer - Pytorch Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch. Install $ pip install segformer-pytorch

Phil Wang 208 Dec 25, 2022
Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Dangers of Bayesian Model Averaging under Covariate Shift This repository contains the code to reproduce the experiments in the paper Dangers of Bayes

Pavel Izmailov 25 Sep 21, 2022
COIN the currently largest dataset for comprehensive instruction video analysis.

COIN Dataset COIN is the currently largest dataset for comprehensive instruction video analysis. It contains 11,827 videos of 180 different tasks (i.e

86 Dec 28, 2022
Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

Cross Transformers - Pytorch (wip) Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch Install $ pip install cross-t

Phil Wang 40 Dec 22, 2022
GraphGT: Machine Learning Datasets for Graph Generation and Transformation

GraphGT: Machine Learning Datasets for Graph Generation and Transformation Dataset Website | Paper Installation Using pip To install the core environm

y6q9 50 Aug 18, 2022
Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

GINC small-scale in-context learning dataset GINC (Generative In-Context learning Dataset) is a small-scale synthetic dataset for studying in-context

P-Lambda 29 Dec 19, 2022
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

[ICCV2021] TransReID: Transformer-based Object Re-Identification [pdf] The official repository for TransReID: Transformer-based Object Re-Identificati

DamoCV 569 Dec 30, 2022
基于YoloX目标检测+DeepSort算法实现多目标追踪Baseline

项目简介: 使用YOLOX+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中。 代码地址(欢迎star): https://github.com/Sharpiless/yolox-deepsort/ 最终效果: 运行demo: python demo

114 Dec 30, 2022
The code for our paper Semi-Supervised Learning with Multi-Head Co-Training

Semi-Supervised Learning with Multi-Head Co-Training (PyTorch) Abstract Co-training, extended from self-training, is one of the frameworks for semi-su

cmc 6 Dec 04, 2022
Unsupervised Pre-training for Person Re-identification (LUPerson)

LUPerson Unsupervised Pre-training for Person Re-identification (LUPerson). The repository is for our CVPR2021 paper Unsupervised Pre-training for Per

143 Dec 24, 2022
An introduction to bioimage analysis - http://bioimagebook.github.io

Introduction to Bioimage Analysis This book tries explain the main ideas of image analysis in a practical and engaging way. It's written primarily for

Bioimage Book 20 Nov 28, 2022
H&M Fashion Image similarity search with Weaviate and DocArray

H&M Fashion Image similarity search with Weaviate and DocArray This example shows how to do image similarity search using DocArray and Weaviate as Doc

Laura Ham 18 Aug 11, 2022
Code for Paper "Evidential Softmax for Sparse MultimodalDistributions in Deep Generative Models"

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models Abstract Many applications of generative models rely on the marginali

Stanford Intelligent Systems Laboratory 9 Jun 06, 2022
Implementing DropPath/StochasticDepth in PyTorch

%load_ext memory_profiler Implementing Stochastic Depth/Drop Path In PyTorch DropPath is available on glasses my computer vision library! Introduction

Francesco Saverio Zuppichini 13 Jan 05, 2023
How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

EV-charging-impact This repository contains the code that has been used for the Queue modelling for the paper "How will electric vehicles affect traff

7 Nov 30, 2022
Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions

Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions Usage Clone the code to local. https://github.com/tanlab/MI

Computational Biology and Machine Learning lab @ TOBB ETU 3 Oct 18, 2022
Implementation of Research Paper "Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation"

Zero-DCE and Zero-DCE++(Lite architechture for Mobile and edge Devices) Papers Abstract The paper presents a novel method, Zero-Reference Deep Curve E

Tauhid Khan 15 Dec 10, 2022