When BERT Plays the Lottery, All Tickets Are Winning

Overview

When BERT Plays the Lottery, All Tickets Are Winning

Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis, using both structured and magnitude pruning. For fine-tuned BERT, we show that (a) it is possible to find subnetworks achieving performance that is comparable with that of the full model, and (b) similarly-sized subnetworks sampled from the rest of the model perform worse. Strikingly, with structured pruning even the worst possible subnetworks remain highly trainable, indicating that most pre-trained BERT weights are potentially useful. We also study the "good" subnetworks to see if their success can be attributed to superior linguistic knowledge, but find them unstable, and not explained by meaningful self-attention patterns.

Environment

Install the requirements in your python 3.7.7 virtual environment.

pip install -r requirements.txt

These experiments were done on multi-gpu environment, were some experiments, benchmarks were run parallel. So some changes to the bash scripts to make it work for your environment.

Dataset

  1. Download the GLUE dataset using data/download_glue.py and data/download_mnli_data.py. Follow the instructions in data/download_glue.py docstring for MRPC.
  2. All data for the tasks should be organized in data/glue/task_name/ structure.
  3. Extract the attention pattern classification labelled data.
    cd data
    tar -xvf head_classification_data.tar.gz

Training, Masking, and Evaluation

Switch cwd to src (cd src) as many paths are relative from that directory.

  1. Fine-tune the BERT on GLUE tasks
./train.sh
  1. Obtain the masks
./find_masks.sh
  1. Train models with the masks applied in good, random and bad settings.
./train_with_masks.sh
  1. Evaluate the trained models
./evaluate.sh

Note: These experiments were run through course of time and now stiched together into single scripts. So it might be better to run the training and evaluation commands in them one by one.

  1. Train the CNN classifier on attention patterns normed and raw.
python classify_attention_patterns.py
python classify_normed_patterns.py

These only train the classifier.

Evaluation Analysis and Final Results

These are primarily done in jupyter notebooks in experiment_analysis directory. There are many experimental notebooks there. Here are the important ones used to generate results included in the paper.

  1. Importance pruning Heatmaps. Ignore the final "train_subset" and "hans" settings.
  2. Magnitude pruning Heatmap
  3. Overlap of surviving components
  4. Generate the random baseline
  5. Attention Classification Patterns
  6. Evaluation Result Comparisons and table
  7. Statistics on mask correlation across seeds
Owner
Sai
Machine Learning Researcher - NLP
Sai
CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images

Code and result about CCAFNet(IEEE TMM) 'CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images' IEE

zyrant丶 14 Dec 29, 2021
GLNet for Memory-Efficient Segmentation of Ultra-High Resolution Images

GLNet for Memory-Efficient Segmentation of Ultra-High Resolution Images Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-

VITA 298 Dec 12, 2022
ByteTrack(Multi-Object Tracking by Associating Every Detection Box)のPythonでのONNX推論サンプル

ByteTrack-ONNX-Sample ByteTrack(Multi-Object Tracking by Associating Every Detection Box)のPythonでのONNX推論サンプルです。 ONNXに変換したモデルも同梱しています。 変換自体を試したい方はByteT

KazuhitoTakahashi 16 Oct 26, 2022
Code for the paper "How Attentive are Graph Attention Networks?"

How Attentive are Graph Attention Networks? This repository is the official implementation of How Attentive are Graph Attention Networks?. The PyTorch

175 Dec 29, 2022
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

MTTS-CAN: Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement Paper Xin Liu, Josh Fromm, Shwetak Patel, Daniel M

Xin Liu 106 Dec 30, 2022
Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"

Memory Compressed Attention Implementation of the Self-Attention layer of the proposed Memory-Compressed Attention, in Pytorch. This repository offers

Phil Wang 47 Dec 23, 2022
Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction

Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction Official github repository for the paper High Fidelity De

28 Dec 16, 2022
Few-shot Learning of GPT-3

Few-shot Learning With Language Models This is a codebase to perform few-shot "in-context" learning using language models similar to the GPT-3 paper.

Tony Z. Zhao 224 Dec 28, 2022
Using LSTM to detect spoofing attacks in an Air-Ground network

Using LSTM to detect spoofing attacks in an Air-Ground network Specifications IDE: Spider Packages: Tensorflow 2.1.0 Keras NumPy Scikit-learn Matplotl

Tiep M. H. 1 Nov 20, 2021
High-fidelity 3D Model Compression based on Key Spheres

High-fidelity 3D Model Compression based on Key Spheres This repository contains the implementation of the paper: Yuanzhan Li, Yuqi Liu, Yujie Lu, Siy

5 Oct 11, 2022
BC3407-Group-5-Project - BC3407 Group Project With Python

BC3407-Group-5-Project As the world struggles to contain the ever-changing varia

1 Jan 26, 2022
Jupyter notebooks showing best practices for using cx_Oracle, the Python DB API for Oracle Database

Python cx_Oracle Notebooks, 2022 The repository contains Jupyter notebooks showing best practices for using cx_Oracle, the Python DB API for Oracle Da

Christopher Jones 13 Dec 15, 2022
PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech

PortaSpeech - PyTorch Implementation PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech. Model Size Module Nor

Keon Lee 279 Jan 04, 2023
Download and preprocess popular sequential recommendation datasets

Sequential Recommendation Datasets This repository collects some commonly used sequential recommendation datasets in recent research papers and provid

125 Dec 06, 2022
Out of Distribution Detection on Natural Adversarial Examples

OOD-on-NAE Research project on out of distribution detection for the Computer Vision course by Prof. Rob Fergus (CSCI-GA 2271) Paper out on arXiv - ht

Anugya 1 Jun 08, 2022
UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.

Unified Multi-modal Transformers This repository maintains the official implementation of the paper UMT: Unified Multi-modal Transformers for Joint Vi

Applied Research Center (ARC), Tencent PCG 84 Jan 04, 2023
Example of a Quantum LSTM

Example of a Quantum LSTM

Riccardo Di Sipio 36 Oct 31, 2022
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

ClevrTex This repository contains dataset generation code for ClevrTex benchmark from paper: ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi

Laurynas Karazija 26 Dec 21, 2022
Official code release for "GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis"

GRAF This repository contains official code for the paper GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis. You can find detailed usage i

349 Dec 29, 2022
Alphabetical Letter Recognition

DecisionTrees-Image-Classification Alphabetical Letter Recognition In these demo we are using "Decision Trees" Our database is composed by Learning Im

Mohammed Firass 4 Nov 30, 2021