Reproducibility package for the paper:
Lucas Maystre, Nagarjuna Kumarappan, Judith Bütepage, Mounia Lalmas. Collaborative Classification from Noisy Labels, AISTATS 2021.
This repository contains
- a reference implementation of the algorithms presented in the paper, and
- Jupyter notebooks enabling the reproduction of some of the experiments.
Our codebase was tested with Python 3.8. The following libraries are required:
numpy(tested with version 1.19.2)
scipy(tested with version 1.6.2)
matplotlib(tested with version 3.3.4)
numba(tested with version 0.53.1)
notebook(tested with version 6.3.0)
To get started, follow these steps:
- Clone the repo locally with:
git clone https://github.com/spotify-research/collabclass.git
- Move to the repository:
- Install the dependencies:
pip install -r requirements.txt
- Install the package:
pip install -e lib/
- Move to the notebook folder:
- Start a notebook server:
Create a new issue
We feel that a welcoming community is important and we ask that you follow Spotify's Open Source Code of Conduct in all interactions with the community.
A full list of contributors can be found on GitHub.
Follow @SpotifyResearch on Twitter for updates.
Copyright 2021 Spotify, Inc.
Licensed under the Apache License, Version 2.0: https://www.apache.org/licenses/LICENSE-2.0
Please report sensitive security issues via Spotify's bug-bounty program (https://hackerone.com/spotify) rather than GitHub.