LibMTL

LibMTL is an open-source library built on PyTorch for Multi-Task Learning (MTL). See the latest documentation for detailed introductions and API instructions.

:star: Star us on GitHub — it motivates us a lot!

:bangbang: A comprehensive survey on Gradient-based Multi-Objective Deep Learning is now available on arXiv, along with an awesome list. Check it out!

News

• [Apr 21 2025] Added support for UPGrad.
• [Feb 18 2025] Added support for a bilevel method Auto-Lambda (TMLR 2022).
• [Feb 17 2025] Added support for FAMO (NeurIPS 2023), SDMGrad (NeurIPS 2023), and MoDo (NeurIPS 2023; JMLR 2024).
• [Feb 06 2025] Added support for two bilevel methods: MOML (NeurIPS 2021; AIJ 2024), FORUM (ECAI 2024).
• [Sep 19 2024] Added support for FairGrad (ICML 2024).
• [Aug 31 2024] Added support for ExcessMTL (ICML 2024).
• [Jul 24 2024] Added support for STCH (ICML 2024).
• [Feb 08 2024] Added support for DB-MTL.
• [Aug 16 2023]: Added support for MoCo (ICLR 2023). Many thanks to the author's help @heshandevaka.
• [Jul 11 2023] Paper got accepted to JMLR.
• [Jun 19 2023] Added support for Aligned-MTL (CVPR 2023).
• [Mar 10 2023]: Added QM9 and PAWS-X examples.
• [Jul 22 2022]: Added support for Nash-MTL (ICML 2022).
• [Jul 21 2022]: Added support for Learning to Branch (ICML 2020). Many thanks to @yuezhixiong (#14).
• [Mar 29 2022]: Paper is now available on the arXiv.

Table of Content

• Features
• Overall Framework
• Supported Algorithms
• Supported Benchmark Datasets
• Installation
• Quick Start
  • Download Dataset
  • Run a Model
• Citation
• Contributor
• Contact Us
• Acknowledgements
• License

Features

• Unified: LibMTL provides a unified code base to implement and a consistent evaluation procedure including data processing, metric objectives, and hyper-parameters on several representative MTL benchmark datasets, which allows quantitative, fair, and consistent comparisons between different MTL algorithms.
• Comprehensive: LibMTL supports many state-of-the-art MTL methods including 8 architectures and 16 optimization strategies. Meanwhile, LibMTL provides a fair comparison of several benchmark datasets covering different fields.
• Extensible: LibMTL follows the modular design principles, which allows users to flexibly and conveniently add customized components or make personalized modifications. Therefore, users can easily and fast develop novel optimization strategies and architectures or apply the existing MTL algorithms to new application scenarios with the support of LibMTL.

Overall Framework

Each module is introduced in Docs.

Supported Algorithms

LibMTL currently supports the following algorithms:

Supported Benchmark Datasets

Installation

1. Create a virtual environment

   conda create -n libmtl python=3.10
   conda activate libmtl
   

2. Clone the repository

   git clone https://github.com/median-research-group/LibMTL.git
   

3. Install LibMTL

   pip install torch==2.3.0+cu121 torchvision==0.18.0+cu121 -f https://download.pytorch.org/whl/torch_stable.html
   pip install torch-scatter==2.1.2+pt23cu121 torch_sparse==0.6.18+pt23cu121 -f https://pytorch-geometric.com/whl/torch-2.3.0+cu121.html
   
   cd LibMTL
   pip install -r requirements.txt
   pip install -e .
   

Quick Start

We use the NYUv2 dataset as an example to show how to use LibMTL.

Download Dataset

The NYUv2 dataset we used is pre-processed by mtan. You can download this dataset here.

Run a Model

The complete training code for the NYUv2 dataset is provided in examples/nyu. The file main.py is the main file for training on the NYUv2 dataset.

You can find the command-line arguments by running the following command.

python main.py -h

For instance, running the following command will train an MTL model with EW and HPS on NYUv2 dataset.

python main.py --weighting EW --arch HPS --dataset_path /path/to/nyuv2 --gpu_id 0 --scheduler step --mode train --save_path PATH

More details is represented in Docs.

Citation

If you find LibMTL useful for your research or development, please cite the following:

@article{lin2023libmtl,
  title={{LibMTL}: A {P}ython Library for Multi-Task Learning},
  author={Baijiong Lin and Yu Zhang},
  journal={Journal of Machine Learning Research},
  volume={24},
  number={209},
  pages={1--7},
  year={2023}
}

Contributor

LibMTL is developed and maintained by Baijiong Lin.

Contact Us

If you have any question or suggestion, please feel free to contact us by raising an issue or sending an email to bj.lin.email@gmail.com.

Acknowledgements

We would like to thank the authors that release the public repositories (listed alphabetically): CAGrad, dselect_k_moe, MultiObjectiveOptimization, mtan, MTL, nash-mtl, pytorch_geometric, and xtreme.

License

LibMTL is released under the MIT license.