Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"

同类别比较
名称	排名	指标
lucidrains/mlp-mixer-pytorch	11,782	语言: Python 星标数: 1,068 分叉数: 107 简介: An All-MLP solution for Vision, from Google AI
NVIDIA/sentiment-discovery	11,786	语言: Python 星标数: 1,067 分叉数: 208 简介: Unsupervised Language Modeling at scale for robust sentiment classification
X-LANCE/SLAM-LLM	11,788	语言: Python 星标数: 1,066 分叉数: 119 简介: A Framework for Speech, Language, Audio, Music Processing with Large Language Model
ctlllll/LLM-ToolMaker	11,789	语言: Jupyter Notebook 星标数: 1,066 分叉数: 97
openai/summarize-from-feedback	11,798	语言: Python 星标数: 1,065 分叉数: 154 简介: Code for "Learning to summarize from human feedback"
jsyoon0823/TimeGAN	11,804	语言: Jupyter Notebook 星标数: 1,064 分叉数: 325 简介: Codebase for Time-series Generative Adversarial Networks (TimeGAN) - NeurIPS 2019
J535D165/recordlinkage	11,807	语言: Python 星标数: 1,063 分叉数: 153 简介: A powerful and modular toolkit for record linkage and duplicate detection in Python
facebookresearch/mbrl-lib	11,811	语言: Python 星标数: 1,063 分叉数: 173 简介: Library for Model Based RL

名称

排名

指标

lucidrains/mlp-mixer-pytorch

11,782

语言:: Python
星标数:: 1,068
分叉数:: 107
简介:: An All-MLP solution for Vision, from Google AI

NVIDIA/sentiment-discovery

11,786

语言:: Python
星标数:: 1,067
分叉数:: 208
简介:: Unsupervised Language Modeling at scale for robust sentiment classification

X-LANCE/SLAM-LLM

11,788

语言:: Python
星标数:: 1,066
分叉数:: 119
简介:: A Framework for Speech, Language, Audio, Music Processing with Large Language Model

ctlllll/LLM-ToolMaker

11,789

语言:: Jupyter Notebook
星标数:: 1,066
分叉数:: 97

openai/summarize-from-feedback

11,798

语言:: Python
星标数:: 1,065
分叉数:: 154
简介:: Code for "Learning to summarize from human feedback"

jsyoon0823/TimeGAN

11,804

语言:: Jupyter Notebook
星标数:: 1,064
分叉数:: 325
简介:: Codebase for Time-series Generative Adversarial Networks (TimeGAN) - NeurIPS 2019

J535D165/recordlinkage

11,807

语言:: Python
星标数:: 1,063
分叉数:: 153
简介:: A powerful and modular toolkit for record linkage and duplicate detection in Python

facebookresearch/mbrl-lib

11,811

语言:: Python
星标数:: 1,063
分叉数:: 173
简介:: Library for Model Based RL

关键参数与规格
参数	值
语言	Python
类别	Model Development
子类别	Deep Learning Frameworks
星标数	1,066
分叉数	173
贡献者	4
创建日期	2019-01-24
更新日期	2026-09-19
1 天星标数	0
7 天星标数	0
排名	11,792
上次排名	11,715
排名变化	-77
7 天星标排名	13,136
上次 7 天星标排名	13,159
7 天星标排名变化	23
总星标排名	10,627
上次总星标排名	10,610
总星标排名变化	-17

参数

值

语言

Python

类别

Model Development

子类别

Deep Learning Frameworks

星标数

1,066

分叉数

173

贡献者

创建日期

2019-01-24

更新日期

2026-09-19

1 天星标数

7 天星标数

排名

11,792

上次排名

11,715

排名变化

-77

7 天星标排名

13,136

上次 7 天星标排名

13,159

7 天星标排名变化

总星标排名

10,627

上次总星标排名

10,610

总星标排名变化

-17

DISCONTINUATION OF PROJECT

This project will no longer be maintained by Intel.
Intel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.
Intel no longer accepts patches to this project.
If you have an ongoing need to use this project, are interested in independently developing it, or would like to maintain patches for the open source software community, please create your own fork of this project.

Multi-Task Learning as Multi-Objective Optimization

This code repository includes the source code for the Paper:

Multi-Task Learning as Multi-Objective Optimization
Ozan Sener, Vladlen Koltun
Neural Information Processing Systems (NeurIPS) 2018

The experimentation framework is based on PyTorch; however, the proposed algorithm (MGDA_UB) is implemented largely Numpy with no other requirement. So, it should be trivial to extend to other deep learning frameworks. PyTorch version is implemented in min_norm_solvers.py, generic version using only Numpy is implemented in file min_norm_solvers_numpy.py.

This repo includes more than the implementation of the paper. It imlpements both Frank-Wolfe and projected gradient descent method. It also has smart initialization and gradient normalization tricks which are described with inline comments.

The source code and dataset (MultiMNIST) are released under the MIT License. See the License file for details.

Requirements and References

The code uses the following Python packages and they are required: tensorboardX, pytorch, click, numpy, torchvision, tqdm, scipy, Pillow

The code is only tested in Python 3 using Anaconda environment.

We adapt and use some code snippets from:

Usage

The code base uses configs.json for the global configurations like dataset directories, etc.. Experiment specific parameters are provided seperately as a json file. See the sample.json for an example.

To train a model, use the command:

python multi_task/train_multi_task.py --param_file=./sample.json

Contact

For any question, you can contact ozan.sener@intel.com

Citation

If you use this codebase or any part of it for a publication, please cite:

@incollection{NeurIPS2018_Sener_Koltun,
title = {Multi-Task Learning as Multi-Objective Optimization},
author = {Sener, Ozan and Koltun, Vladlen},
booktitle = {Advances in Neural Information Processing Systems 31},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {525--536},
year = {2018},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/7334-multi-task-learning-as-multi-objective-optimization.pdf}
}

MultiObjectiveOptimization

记录了多少星标和分叉？

仓库排名是多少？

记录的语言和类别是什么？

哪个仓库排名最接近？