Code for Environment Inference for Invariant Learning (ICML 2020 UDL Workshop Paper)

Elliot Creager

Last update: Dec 9, 2022

Related tags

Deep Learning eiil

Overview

Environment Inference for Invariant Learning

This code accompanies the paper Environment Inference for Invariant Learning, which appears at ICML 2021.

Thanks to my wonderful co-authors Jörn-Henrik Jacobsen and Richard Zemel.

The InvariantRiskMinimization subdirectory is modified from https://github.com/facebookresearch/InvariantRiskMinimization, and has its own license.

Reproducing paper results

Sythetic data

To produce results

cd InvariantRiskMinimization/code/experiment_synthetic/
./run_sems.sh

To analyze results

noteooks/sem_results.ipynb

Color MNIST

To produce results

./exps/cmnist_label_noise_sweep.sh

To analyze results

notebooks/plot_cmnist_label_noise_sweep.ipynb

As an alternative, InvariantRiskMinimization/code/colored_mnist/optimize_envs.sh also runs EIIL+IRM on CMNIST with 25% label noise (the default from the IRM paper).

Citing this work

If you find this code to your research useful please consider citing our workshop paper using the following bibtex entry

@inproceedings{creager21environment,
  title={Environment Inference for Invariant Learning},
  author={Creager, Elliot and Jacobsen, J{\"o}rn-Henrik and Zemel, Richard},
  booktitle={International Conference on Machine Learning},
  year={2021},
}

You might also like...

This is an implementation for the CVPR2020 paper "Learning Invariant Representation for Unsupervised Image Restoration"

Learning Invariant Representation for Unsupervised Image Restoration (CVPR 2020) Introduction This is an implementation for the paper "Learning Invari

88 Nov 7, 2022

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Code accompanying "Dynamic Neural Relational Inference" This codebase accompanies the paper "Dynamic Neural Relational Inference" from CVPR 2020. This

48 Dec 23, 2022

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

NeuralTextures This is repository with inference code for paper "StylePeople: A Generative Model of Fullbody Human Avatars" (CVPR21). This code is for

Visual Understanding Lab @ Samsung AI Center Moscow

18 Oct 6, 2022

Comments

Could you please also share the codes for other datasets?

Hi! I really like this excellent paper! The work is very brilliant and insightful! I am working on reproducing the results and applying EIIL to our projects. I wonder if you could please share the codes for other datasets including Waterbirds, Adult, and CivilComments. I'll really appreciate it!

opened by ghzhang233 0

Code for Environment Inference for Invariant Learning (ICML 2020 UDL Workshop Paper)

Related tags

Overview

Environment Inference for Invariant Learning

Reproducing paper results

Sythetic data

Color MNIST

Citing this work

You might also like...

This is an implementation for the CVPR2020 paper "Learning Invariant Representation for Unsupervised Image Restoration"

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Code for ICML 2021 paper: How could Neural Networks understand Programs?

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Code for Fold2Seq paper from ICML 2021

Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun

Comments

Could you please also share the codes for other datasets?

Owner

Elliot Creager

The implementation of the algorithm in the paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020.

Code for Transformer Hawkes Process, ICML 2020.

[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

Decentralized Reinforcment Learning: Global Decision-Making via Local Economic Transactions (ICML 2020)

PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).

PERIN is Permutation-Invariant Semantic Parser developed for MRP 2020

Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

Code for NeurIPS 2021 paper: Invariant Causal Imitation Learning for Generalizable Policies

Sign Language Translation with Transformers (COLING'2020, ECCV'20 SLRTP Workshop)

The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition.