Skip to main content

AlignReg

AlignReg

Alignment Regularization with Data Augmentation

Implementation of the AlignReg package associated with the following paper:

Haohan Wang, Zeyi Huang, Xindi Wu, and Eric P. Xing. 2022. Toward Learning Robust and Invariant Representations with Alignment Regular- ization and Data Augmentation. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22), August 14–18, 2022, Washington, DC, USA. ACM, New York, NY, USA,

The package is organized by Hanru Yan

Installation

One can direclty install the package with

  pip install alignreg 

Or one can download the code and use it locally.

Usage Tutorial

One can use the package in simply one line of code.

Please visit the iPython example for usage instructions in both TensorFlow and PyTorch.

Replication:

This repository serves for the purpose to guide others to use our tool, if you are interested in the scripts to replicate our results in paper, please contact us and we will share the repository for replication.

Contact

Haohan Wang · Hanru Yan

Release files for alignreg 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for alignreg 1.0.1
File Size Uploaded
alignreg-1.0.1.tar.gz 5.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for alignreg 1.0.1
File Interpreter ABI Platform
alignreg-1.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 12.0 kB

Release files / alignreg-1.0.1.tar.gz

Download URL alignreg-1.0.1.tar.gz
Size 5.2 kB
Tags Source
SHA-256 checksum
How to use checksums
654ebd3426fab0dfa6a07c8bf01be1e8d92c8cb0b52b374f8673630da15a2bc4
BLAKE2b-256 checksum
How to use checksums
751d6ab4f6c784a0d5b5e4d5e827b0c0bc8802bc02a1176fa9106b2a6ba9afca
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.9 tqdm/4.64.0 importlib-metadata/4.8.3 keyring/23.4.1 rfc3986/1.5.0 colorama/0.4.4 CPython/3.6.9

Release files / alignreg-1.0.1-py3-none-any.whl

Download URL alignreg-1.0.1-py3-none-any.whl
Size 6.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9a50ece7ad939f84569efd818266d1e6bedb765a0bf24b71e0add95fe855b9b9
BLAKE2b-256 checksum
How to use checksums
8956612e6b5fa24883596fb44dab561ed12d674008bdac44a1c07e067b39ee43
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.9 tqdm/4.64.0 importlib-metadata/4.8.3 keyring/23.4.1 rfc3986/1.5.0 colorama/0.4.4 CPython/3.6.9

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 release files

1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page