BalancingGroups

Code to replicate the experimental results from Simple data balancing baselines achieve competitive worst-group-accuracy.

Replicating the main results

Set environment variables

export DATASETS_PATH=/path/to/datasets
export SLURM_PATH=/path/to/slurm/logs

Download and extract datasets

Waterbirds to $DATASETS_PATH/waterbirds
CelebA to $DATASETS_PATH/celeba
CivilComments to $DATASETS_PATH/civilcomments
MultiNLI to $DATASETS_PATH/multinli

Generate dataset metadata

cd metadata/
python generate_metadata_waterbirds.py
python generate_metadata_celeba.py
python generate_metadata_civilcomments.py
python generate_metadata_multinli.py
cd ..

Launch jobs

# Launching 1400 combo seeds = 50 hparams for 4 datasets for 7 algorithms
# Each combo seed is ran 5 times to compute error bars, totalling 7000 jobs
./train.py --output_dir main_sweep --num_hparams_seeds 1400

Parse results

./parse.py main_sweep

License

This source code is released under the CC-BY-NC license, included here.

Simple data balancing baselines for worst-group-accuracy benchmarks.

Related tags

Overview

BalancingGroups

Replicating the main results

Set environment variables

Download and extract datasets

Generate dataset metadata

Launch jobs

Parse results

License

Owner

Facebook Research

Learning --> Numpy January 2022 - winter'22

Coursera Machine Learning - Python code

Management of exclusive GPU access for distributed machine learning workloads

Probabilistic programming framework that facilitates objective model selection for time-varying parameter models.

AutoTabular automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications.

A collection of neat and practical data science and machine learning projects

To design and implement the Identification of Iris Flower species using machine learning using Python and the tool Scikit-Learn.

Machine learning algorithms implementation

Adaptive: parallel active learning of mathematical functions

A Python toolbox to churn out organic alkalinity calculations with minimal brain engagement.

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker

Required for a machine learning pipeline data preprocessing and variable engineering script needs to be prepared

MLOps pipeline project using Amazon SageMaker Pipelines

Basic Docker Compose for Machine Learning Purposes

Machine Learning Model to predict the payment date of an invoice when it gets created in the system.

A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.

Automated Machine Learning Pipeline for tabular data. Designed for predictive maintenance applications, failure identification, failure prediction, condition monitoring, etc.

Python module for data science and machine learning users.

A toolkit for geo ML data processing and model evaluation (fork of solaris)

A simple python program which predicts the success of a movie based on it's type, actor, actress and director