{"id":19529274,"url":"https://github.com/isl-org/multiobjectiveoptimization","last_synced_at":"2025-04-12T23:33:10.179Z","repository":{"id":41194330,"uuid":"167348905","full_name":"isl-org/MultiObjectiveOptimization","owner":"isl-org","description":"Source code for Neural Information Processing Systems (NeurIPS) 2018 paper \"Multi-Task Learning as Multi-Objective Optimization\"","archived":false,"fork":false,"pushed_at":"2021-04-12T09:49:11.000Z","size":32,"stargazers_count":935,"open_issues_count":10,"forks_count":170,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-05-18T21:43:22.132Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/isl-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-01-24T10:26:57.000Z","updated_at":"2024-05-18T16:11:15.000Z","dependencies_parsed_at":"2022-08-10T01:43:06.268Z","dependency_job_id":null,"html_url":"https://github.com/isl-org/MultiObjectiveOptimization","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FMultiObjectiveOptimization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FMultiObjectiveOptimization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FMultiObjectiveOptimization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/isl-org%2FMultiObjectiveOptimization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/isl-org","download_url":"https://codeload.github.com/isl-org/MultiObjectiveOptimization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248647258,"owners_count":21139081,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T01:23:17.206Z","updated_at":"2025-04-12T23:33:10.158Z","avatar_url":"https://github.com/isl-org.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DISCONTINUATION OF PROJECT #  \nThis project will no longer be maintained by Intel.  \nIntel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.  \nIntel no longer accepts patches to this project.  \n 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.  \n  \n# Multi-Task Learning as Multi-Objective Optimization\n\nThis code repository includes the source code for the [Paper](https://arxiv.org/abs/1810.04650):\n\n```\nMulti-Task Learning as Multi-Objective Optimization\nOzan Sener, Vladlen Koltun\nNeural Information Processing Systems (NeurIPS) 2018 \n```\n\nThe 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`.\n\nThis 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.\n\nThe source code and dataset (MultiMNIST) are released under the MIT License. See the License file for details.\n\n\n# Requirements and References\nThe code uses the following Python packages and they are required: ``tensorboardX, pytorch, click, numpy, torchvision, tqdm, scipy, Pillow``\n\nThe code is only tested in ``Python 3`` using ``Anaconda`` environment.\n\nWe adapt and use some code snippets from:\n* [CSAILVision Semanti Segmentation](https://github.com/CSAILVision/semantic-segmentation-pytorch)\n* [PyTorch-SemSeg](https://github.com/meetshah1995/pytorch-semseg/)\n\n\n\n# Usage\nThe 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.\n\nTo train a model, use the command: \n```bash\npython multi_task/train_multi_task.py --param_file=./sample.json\n```\n\n# Contact\nFor any question, you can contact ozan.sener@intel.com\n\n# Citation\nIf you use this codebase or any part of it for a publication, please cite:\n```\n@incollection{NeurIPS2018_Sener_Koltun,\ntitle = {Multi-Task Learning as Multi-Objective Optimization},\nauthor = {Sener, Ozan and Koltun, Vladlen},\nbooktitle = {Advances in Neural Information Processing Systems 31},\neditor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},\npages = {525--536},\nyear = {2018},\npublisher = {Curran Associates, Inc.},\nurl = {http://papers.nips.cc/paper/7334-multi-task-learning-as-multi-objective-optimization.pdf}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fmultiobjectiveoptimization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fisl-org%2Fmultiobjectiveoptimization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fisl-org%2Fmultiobjectiveoptimization/lists"}