[ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Overview

AMOS

This repository contains the scripts for fine-tuning AMOS pretrained models on GLUE and SQuAD 2.0 benchmarks.

Paper: Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Overview

We provide the scripts in two versions, based on two widely-used open-source codebases, the Fairseq Library and the Huggingface Transformers Library. The two code versions are mostly equivalent in functionality, and you are free to use either of them. However, we note that the fairseq version is what we used in our experiments, and it will best reproduce the results in the paper; the huggingface version is implemented later to provide compatibility with the Huggingface Transformers Library, and may yield slightly different results.

Please follow the README files under the two directories for running the code.

GLUE Fine-Tuning Results

The General Language Understanding Evaluation (GLUE) benchmark is a collection of sentence- or sentence-pair language understanding tasks for evaluating and analyzing natural language understanding systems.

GLUE dev set results of AMOS base++ model are as follows (median of 5 different random seeds):

Model MNLI-m/mm QQP QNLI SST-2 CoLA RTE MRPC STS-B AVG
AMOS base++ 90.5/90.4 92.4 94.4 95.5 71.8 86.6 91.7 92.0 89.4

GLUE test set results of AMOS base++ model are as follows (no ensemble, task-specific tricks, etc.):

Model MNLI-m/mm QQP QNLI SST-2 CoLA RTE MRPC STS-B AVG
AMOS base++ 90.4/89.9 90.2 94.6 96.8 69.2 83.6 88.9 91.3 88.1

SQuAD 2.0 Fine-Tuning Results

Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.

SQuAD 2.0 dev set results of AMOS base++ and large++ models are as follows (median of 5 different random seeds):

Model EM F1
AMOS base++ 85.0 87.9

Citation

If you find the code and models useful for your research, please cite the following paper:

@inproceedings{meng2022amos,
  title={Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators},
  author={Meng, Yu and Xiong, Chenyan and Bajaj, Payal and Tiwary, Saurabh and Bennett, Paul and Han, Jiawei and Song, Xia},
  booktitle={International Conference on Learning Representations},
  year={2022}
}

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.

Issues
  • Bump numpy from 1.21.2 to 1.22.0 in /huggingface

    Bump numpy from 1.21.2 to 1.22.0 in /huggingface

    Bumps numpy from 1.21.2 to 1.22.0.

    Release notes

    Sourced from numpy's releases.

    v1.22.0

    NumPy 1.22.0 Release Notes

    NumPy 1.22.0 is a big release featuring the work of 153 contributors spread over 609 pull requests. There have been many improvements, highlights are:

    • Annotations of the main namespace are essentially complete. Upstream is a moving target, so there will likely be further improvements, but the major work is done. This is probably the most user visible enhancement in this release.
    • A preliminary version of the proposed Array-API is provided. This is a step in creating a standard collection of functions that can be used across application such as CuPy and JAX.
    • NumPy now has a DLPack backend. DLPack provides a common interchange format for array (tensor) data.
    • New methods for quantile, percentile, and related functions. The new methods provide a complete set of the methods commonly found in the literature.
    • A new configurable allocator for use by downstream projects.

    These are in addition to the ongoing work to provide SIMD support for commonly used functions, improvements to F2PY, and better documentation.

    The Python versions supported in this release are 3.8-3.10, Python 3.7 has been dropped. Note that 32 bit wheels are only provided for Python 3.8 and 3.9 on Windows, all other wheels are 64 bits on account of Ubuntu, Fedora, and other Linux distributions dropping 32 bit support. All 64 bit wheels are also linked with 64 bit integer OpenBLAS, which should fix the occasional problems encountered by folks using truly huge arrays.

    Expired deprecations

    Deprecated numeric style dtype strings have been removed

    Using the strings "Bytes0", "Datetime64", "Str0", "Uint32", and "Uint64" as a dtype will now raise a TypeError.

    (gh-19539)

    Expired deprecations for loads, ndfromtxt, and mafromtxt in npyio

    numpy.loads was deprecated in v1.15, with the recommendation that users use pickle.loads instead. ndfromtxt and mafromtxt were both deprecated in v1.17 - users should use numpy.genfromtxt instead with the appropriate value for the usemask parameter.

    (gh-19615)

    ... (truncated)

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • Training loss and acc/auc curve

    Training loss and acc/auc curve

    Hi, I'm using amos now. My amos model (small size, discriminator ) have a low recall (70-80% percision while 40% recall). 60% mlm acc of generator. I would just like to ask if you can post the loss of both base and large models (or even share the loss training curve, acc curve or auc curve ) so that i have a kind of reference point when training own models. This will help me a lot!

    Thank u.

    opened by wwx13 1
Releases(v0.1.0)
Owner
Microsoft
Open source projects and samples from Microsoft
Microsoft
Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training

Super-Fast-Adversarial-Training This is a PyTorch Implementation code for develo

LBK 23 Jul 4, 2022
Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

Geometry-aware Instance-reweighted Adversarial Training This repository provides codes for Geometry-aware Instance-reweighted Adversarial Training (ht

Jingfeng 47 Jun 14, 2022
Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data - Official PyTorch Implementation (CVPR 2022)

Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data (CVPR 2022) Potentials of primitive shapes f

null 30 Aug 2, 2022
Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Adversarial Training Against Location-Optimized Adversarial Patches arXiv | Paper | Code | Video | Slides Code for the paper: Sukrut Rao, David Stutz,

Sukrut Rao 28 Jun 13, 2022
Official implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis https://arxiv.org/abs/2011.13775

CIPS -- Official Pytorch Implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis Requirements pip install -r requi

Multimodal Lab @ Samsung AI Center Moscow 196 Aug 5, 2022
Official implementation of "GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators" (NeurIPS 2020)

GS-WGAN This repository contains the implementation for GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators (NeurIPS

null 39 Jun 6, 2022
Code for ICCV 2021 paper: ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators..

ARAPReg Code for ICCV 2021 paper: ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators.. Installation The cod

Bo Sun 129 Jul 20, 2022
PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

Maximum Entropy Generators for Energy-Based Models All experiments have tensorboard visualizations for samples / density / train curves etc. To run th

Rithesh Kumar 133 Jul 21, 2022
Pytorch implementation of the paper Progressive Growing of Points with Tree-structured Generators (BMVC 2021)

PGpoints Pytorch implementation of the paper Progressive Growing of Points with Tree-structured Generators (BMVC 2021) Hyeontae Son, Young Min Kim Pre

Hyeontae Son 9 Jun 6, 2022
This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TransUNet This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation Usage

null 1.2k Aug 6, 2022
RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

State Entropy Maximization with Random Encoders for Efficient Exploration (RE3) (ICML 2021) Code for State Entropy Maximization with Random Encoders f

Younggyo Seo 45 Jul 6, 2022
GAN encoders in PyTorch that could match PGGAN, StyleGAN v1/v2, and BigGAN. Code also integrates the implementation of these GANs.

MTV-TSA: Adaptable GAN Encoders for Image Reconstruction via Multi-type Latent Vectors with Two-scale Attentions. This is the official code release fo

owl 34 Jul 12, 2022
PyTorch Implement of Context Encoders: Feature Learning by Inpainting

Context Encoders: Feature Learning by Inpainting This is the Pytorch implement of CVPR 2016 paper on Context Encoders 1) Semantic Inpainting Demo Inst

null 312 Aug 3, 2022
Final project code: Implementing MAE with downscaled encoders and datasets, for ESE546 FA21 at University of Pennsylvania

546 Final Project: Masked Autoencoder Haoran Tang, Qirui Wu 1. Training To train the network, please run mae_pretraining.py. Please modify folder path

Haoran Tang 0 Apr 22, 2022
This repository holds the code for the paper "Deep Conditional Gaussian Mixture Model forConstrained Clustering".

Deep Conditional Gaussian Mixture Model for Constrained Clustering. This repository holds the code for the paper Deep Conditional Gaussian Mixture Mod

null 11 May 11, 2022
SMD-Nets: Stereo Mixture Density Networks

SMD-Nets: Stereo Mixture Density Networks This repository contains a Pytorch implementation of "SMD-Nets: Stereo Mixture Density Networks" (CVPR 2021)

Fabio Tosi 105 Jul 31, 2022
Tutel MoE: An Optimized Mixture-of-Experts Implementation

Project Tutel Tutel MoE: An Optimized Mixture-of-Experts Implementation. Supported Framework: Pytorch Supported GPUs: CUDA(fp32 + fp16), ROCm(fp32) Ho

Microsoft 252 Aug 6, 2022
Audio Source Separation is the process of separating a mixture into isolated sounds from individual sources

Audio Source Separation is the process of separating a mixture into isolated sounds from individual sources (e.g. just the lead vocals).

Victor Basu 11 May 12, 2022
Pytorch implementation of paper: "NeurMiPs: Neural Mixture of Planar Experts for View Synthesis"

NeurMips: Neural Mixture of Planar Experts for View Synthesis This is the official repo for PyTorch implementation of paper "NeurMips: Neural Mixture

James Lin 89 Jul 29, 2022