wwweiwei / Track2Vec

Official Implementation of Track2Vec: Fairness Music Recommendation with a GPU-Free Customizable-Driven Framework EvalRS-CIKM-2022

Track2Vec - Fairness Music Recommendation with a GPU-Free Customizable-Driven Framework

💡 This is the official code of team wwweiwei to the EvalRS Data Challenge. We won the fouth place. For more details, please refer to our paper and brief introduction in our blog.

Usage

Setup

• Build environment

  pip install -r /path/to/requirements.txt
  

• Place your upload.env in the root folder.

Run script

python submission.py

• Notes: Our proposed metric MR-ITF will automatically report in the corresponding json file with other standard metric.

Introduction

• Proposed Framework: Track2Vec

• Proposed Fairness Metric: Miss Rate - Inverse Ground Truth Frequency (MR-ITF)

Citation

If you find our work is relevant to your research, please cite:

@inproceedings{DBLP:conf/cikm/DuWP22,
  author    = {Wei{-}Wei Du and
               Wei{-}Yao Wang and
               Wen{-}Chih Peng},
  title     = {Track2Vec: fairness music recommendation with a GPU-free customizable-driven
               framework},
  booktitle = {{CIKM} Workshops},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {3318},
  publisher = {CEUR-WS.org},
  year      = {2022}
}