AuxiNash

Official implementation of "Auxiliary Learning as an Asymmetric Bargaining Game".

Setup environment

conda create -n auxinash python=3.9
conda activate auxinash
conda install pytorch==1.9.0 torchvision==0.10.0 cudatoolkit=10.2 -c pytorch

Install the repo:

git clone https://github.com/AvivSham/auxinash.git
cd auxinash
pip install -e .

Run experiment

To run NYUv2 experiment:

cd experiment/nyuv2
python trainer.py --method=auxinash

Follow instruction on the experiment README file for more information regarding, e.g., datasets.

You can also replace auxinash with on of the following Auxiliary / MTL methods.

We also support experiment tracking with Weights & Biases with two additional parameters:

python trainer.py --method=auxinash --wandb_project=<project-name> --wandb_entity=<entity-name>

Auxiliary & MTL methods

We support the following Auxiliary & MTL methods with a unified API. To run experiment with MTL method X simply run:

python trainer.py --method=X

Citation

If you find AuxiNash to be useful in your own research, please consider citing the following paper:

@article{shamsian2023auxiliary,
  title={Auxiliary Learning as an Asymmetric Bargaining Game},
  author={Shamsian, Aviv and Navon, Aviv and Glazer, Neta and Kawaguchi, Kenji and Chechik, Gal and Fetaya, Ethan},
  journal={arXiv preprint arXiv:2301.13501},
  year={2023}
}