Self-training with Weak Supervision (NAACL 2021)

Related tags

Deep LearningASTRA
Overview

Self-Training with Weak Supervision

This repo holds the code for our weak supervision framework, ASTRA, described in our NAACL 2021 paper: "Self-Training with Weak Supervision"

Overview of ASTRA

ASTRA is a weak supervision framework for training deep neural networks by automatically generating weakly-labeled data. Our framework can be used for tasks where it is expensive to manually collect large-scale labeled training data.

ASTRA leverages domain-specific rules, a large amount of unlabeled data, and a small amount of labeled data through a teacher-student architecture:

alt text

Main components:

  • Weak Rules: domain-specific rules, expressed as Python labeling functions. Weak supervision usually considers multiple rules that rely on heuristics (e.g., regular expressions) for annotating text instances with weak labels.
  • Student: a base model (e.g., a BERT-based classifier) that provides pseudo-labels as in standard self-training. In contrast to heuristic rules that cover a subset of the instances, the student can predict pseudo-labels for all instances.
  • RAN Teacher: our Rule Attention Teacher Network that aggregates the predictions of multiple weak sources (rules and student) with instance-specific weights to compute a single pseudo-label for each instance.

The following table reports classification results over 6 benchmark datasets averaged over multiple runs.

Method TREC SMS YouTube CENSUS MIT-R Spouse
Majority Voting 60.9 48.4 82.2 80.1 40.9 44.2
Snorkel 65.3 94.7 93.5 79.1 75.6 49.2
Classic Self-training 71.1 95.1 92.5 78.6 72.3 51.4
ASTRA 80.3 95.3 95.3 83.1 76.1 62.3

Our NAACL'21 paper describes our ASTRA framework and more experimental results in detail.

Installation

First, create a conda environment running Python 3.6:

conda create --name astra python=3.6
conda activate astra

Then, install the required dependencies:

pip install -r requirements.txt

Download Data

We will soon add detailed instructions for downloading datasets and domain-specific rules as well as supporting custom datasets.

Running ASTRA

You can run ASTRA as:

cd astra
python main.py --dataset  --student_name  --teacher_name 

Supported < STUDENT > models:

  1. logreg: Bag-of-words Logistic Regression classifier
  2. elmo: ELMO-based classifier
  3. bert: BERT-based classifier

Supported < TEACHER > models:

  1. ran: our Rule Attention Network (RAN)

We will soon add instructions for supporting custom student and teacher components.

Citation

@InProceedings{karamanolakis2021self-training,
author = {Karamanolakis, Giannis and Mukherjee, Subhabrata (Subho) and Zheng, Guoqing and Awadallah, Ahmed H.},
title = {Self-training with Weak Supervision},
booktitle = {NAACL 2021},
year = {2021},
month = {May},
publisher = {NAACL 2021},
url = {https://www.microsoft.com/en-us/research/publication/self-training-weak-supervision-astra/},
}

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

Owner
Microsoft
Open source projects and samples from Microsoft
Microsoft
PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].

Smooth ReLU in PyTorch Unofficial PyTorch reimplementation of the Smooth ReLU (SmeLU) activation function proposed in the paper Real World Large Scale

Christoph Reich 10 Jan 02, 2023
Zalo AI challenge 2021 task hum to song

Zalo AI challenge 2021 task Hum to Song pipeline: Chuẩn bị dữ liệu cho quá trình train: Sửa các file đường dẫn trong config/preprocess.yaml raw_path:

Vo Van Phuc 105 Dec 16, 2022
Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021)

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021) PyTorch implementation of Learning RAW-to-sRGB Mappings with Inaccurat

Zhilu Zhang 53 Dec 20, 2022
A two-stage U-Net for high-fidelity denoising of historical recordings

A two-stage U-Net for high-fidelity denoising of historical recordings Official repository of the paper (not submitted yet): E. Moliner and V. Välimäk

Eloi Moliner Juanpere 57 Jan 05, 2023
A Small and Easy approach to the BraTS2020 dataset (2D Segmentation)

BraTS2020 A Light & Scalable Solution to BraTS2020 | Medical Brain Tumor Segmentation (2D Segmentation) Developed the segmentation models for segregat

Gunjan Haldar 0 Jan 19, 2022
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning By Zhenda Xie*, Yutong Lin*, Zheng Zhang, Yue Ca

Zhenda Xie 293 Dec 20, 2022
Constrained Language Models Yield Few-Shot Semantic Parsers

Constrained Language Models Yield Few-Shot Semantic Parsers This repository contains tools and instructions for reproducing the experiments in the pap

Microsoft 43 Nov 23, 2022
This project is based on RIFE and aims to make RIFE more practical for users by adding various features and design new models

CPM 项目描述 CPM(Chinese Pretrained Models)模型是北京智源人工智能研究院和清华大学发布的中文大规模预训练模型。官方发布了三种规模的模型,参数量分别为109M、334M、2.6B,用户需申请与通过审核,方可下载。 由于原项目需要考虑大模型的训练和使用,需要安装较为复杂

hzwer 190 Jan 08, 2023
CMSC320 - Introduction to Data Science - Fall 2021

CMSC320 - Introduction to Data Science - Fall 2021 Instructors: Elias Jonatan Gonzalez and José Manuel Calderón Trilla Lectures: MW 3:30-4:45 & 5:00-6

Introduction to Data Science 6 Sep 12, 2022
[ECCV 2020] Gradient-Induced Co-Saliency Detection

Gradient-Induced Co-Saliency Detection Zhao Zhang*, Wenda Jin*, Jun Xu, Ming-Ming Cheng ⭐ Project Home » The official repo of the ECCV 2020 paper Grad

Zhao Zhang 35 Nov 25, 2022
Sinkformers: Transformers with Doubly Stochastic Attention

Code for the paper : "Sinkformers: Transformers with Doubly Stochastic Attention" Paper You will find our paper here. Compat This package has been dev

Michael E. Sander 31 Dec 29, 2022
This repository contains the code used to quantitatively evaluate counterfactual examples in the associated paper.

On Quantitative Evaluations of Counterfactuals Install To install required packages with conda, run the following command: conda env create -f requi

Frederik Hvilshøj 1 Jan 16, 2022
Release of the ConditionalQA dataset

ConditionalQA Datasets accompanying the paper ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers. Disclaimer This dataset

14 Oct 17, 2022
Kernel Point Convolutions

Created by Hugues THOMAS Introduction Update 27/04/2020: New PyTorch implementation available. With SemanticKitti, and Windows supported. This reposit

Hugues THOMAS 584 Jan 07, 2023
A foreign language learning aid using a neural network to predict probability of translating foreign words

Langy Langy is a reading-focused foreign language learning aid orientated towards young children. Reading is an activity that every child knows. It is

Shona Lowden 6 Nov 17, 2021
Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs)

Why Spectral Normalization Stabilizes GANs: Analysis and Improvements [paper (NeurIPS 2021)] [paper (arXiv)] [code] Authors: Zinan Lin, Vyas Sekar, Gi

Zinan Lin 32 Dec 16, 2022
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks

MEAL-V2 This is the official pytorch implementation of our paper: "MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tric

Zhiqiang Shen 653 Dec 19, 2022
PG2Net: Personalized and Group PreferenceGuided Network for Next Place Prediction

PG2Net PG2Net:Personalized and Group Preference Guided Network for Next Place Prediction Datasets Experiment results on two Foursquare check-in datase

Urban Mobility 5 Dec 20, 2022
(to be released) [NeurIPS'21] Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs

Higher-Order Transformers Kim J, Oh S, Hong S, Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs, NeurIPS 2021. [arxiv] W

Jinwoo Kim 44 Dec 28, 2022
Redash reset for python

redash-reset This will use a default REDASH_SECRET_KEY key of c292a0a3aa32397cdb050e233733900f this allows you to reset the password of the user ID bu

Robert Wiggins 5 Nov 14, 2022