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

Last update: Nov 06, 2022

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
Set	Model	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
	WARP_init (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
	WARP_init (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 ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Related tags

Overview

🌀 WARP: Word-level Adversarial ReProgramming

Few-Shot Results

Setup

Training

Linear Probing

WARP_0

Training WARP

WARP_init

Few-Shot Experiments

Evaluation

Citation

Owner

YerevaNN

Implementation of "Deep Implicit Templates for 3D Shape Representation"

(Py)TOD: Tensor-based Outlier Detection, A General GPU-Accelerated Framework

[ACM MM 2021] Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Practical Single-Image Super-Resolution Using Look-Up Table

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

This repository contains code demonstrating the methods outlined in Path Signature Area-Based Causal Discovery in Coupled Time Series presented at Causal Analysis Workshop 2021.

ruptures: change point detection in Python

This package implements the algorithms introduced in Smucler, Sapienza, and Rotnitzky (2020) to compute optimal adjustment sets in causal graphical models.

Rainbow DQN implementation that outperforms the paper's results on 40% of games using 20x less data 🌈

Advantage Actor Critic (A2C): jax + flax implementation

QAHOI: Query-Based Anchors for Human-Object Interaction Detection (paper)

This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Motion .

[KDD 2021, Research Track] DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

The code for SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network.

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

A repository for the updated version of CoinRun used to collect MUGEN, a multimodal video-audio-text dataset.

EMNLP 2020 - Summarizing Text on Any Aspects

This is the offical website for paper ''Category-consistent deep network learning for accurate vehicle logo recognition''

Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT