{"id":38699778,"url":"https://github.com/intsystems/bmm-multitask-learning","last_synced_at":"2026-01-17T10:45:54.917Z","repository":{"id":282242336,"uuid":"934943278","full_name":"intsystems/bmm-multitask-learning","owner":"intsystems","description":"Multitask learning techniques implemented in Python","archived":false,"fork":false,"pushed_at":"2025-05-12T23:31:12.000Z","size":6449,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-05-13T00:28:27.416Z","etag":null,"topics":["edu-project","multitask-learning","pytorch"],"latest_commit_sha":null,"homepage":"https://intsystems.github.io/bmm-multitask-learning/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/intsystems.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-18T16:47:44.000Z","updated_at":"2025-05-12T23:28:54.000Z","dependencies_parsed_at":"2025-04-13T22:20:03.815Z","dependency_job_id":"68a7625d-cdb1-4a65-9072-b2dc0e48f787","html_url":"https://github.com/intsystems/bmm-multitask-learning","commit_stats":null,"previous_names":["intsystems/bmm-multitask-learning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/intsystems/bmm-multitask-learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intsystems%2Fbmm-multitask-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intsystems%2Fbmm-multitask-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intsystems%2Fbmm-multitask-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intsystems%2Fbmm-multitask-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intsystems","download_url":"https://codeload.github.com/intsystems/bmm-multitask-learning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intsystems%2Fbmm-multitask-learning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28506593,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T10:25:30.148Z","status":"ssl_error","status_checked_at":"2026-01-17T10:25:29.718Z","response_time":85,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["edu-project","multitask-learning","pytorch"],"created_at":"2026-01-17T10:45:54.625Z","updated_at":"2026-01-17T10:45:54.908Z","avatar_url":"https://github.com/intsystems.png","language":"Python","readme":"# BMM Multitask Learning\n\n[![Python Version](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/)\n![PyTorch](https://img.shields.io/badge/PyTorch-%23EE4C2C.svg?style=for-the-badge\u0026logo=PyTorch\u0026logoColor=white)\n[![test_and_docs](https://github.com/intsystems/bmm-multitask-learning/actions/workflows/test_and_deploy.yaml/badge.svg)](https://github.com/intsystems/bmm-multitask-learning/actions/workflows/test_and_deploy.yaml)\n\nMulti-task learning is a machine learning paradigm which involves optimization model parameters for multiple diverse tasks. Vanilla multitask optimization presumes that the tasks are optimized without any hierarchy, but with some possilbe weights over tasks. This is an *educational project* which aims to implement different methods to assign weights or hierarchy to tasks to make the optimization more effective. We use *python* and [*pytorch*](https://docs.pytorch.org/docs/stable/index.html) as a computational framework.\n\n## Implemented algorithms\n\n* [Task clustering](https://jmlr.csail.mit.edu/papers/volume4/bakker03a/bakker03a.pdf)\n* [Bayesian Multitask Learning with Latent Hierarchies](https://arxiv.org/pdf/1408.2032)\n* [Sparse Bayesian Multi-Task Learning](https://proceedings.neurips.cc/paper_files/paper/2011/file/4fac9ba115140ac4f1c22da82aa0bc7f-Paper.pdf)\n* [Variational method](https://proceedings.neurips.cc/paper_files/paper/2021/file/afd4836712c5e77550897e25711e1d96-Paper.pdf)\n\n## Coverage report\n\nCan be found on [pages](https://intsystems.github.io/bmm-multitask-learning/coverage/).\n\n## Documentation\n\nCurrent documentation is available on [pages](https://intsystems.github.io/bmm-multitask-learning/).\n\nKey sections:\n\n* API Reference\n* Theory and Mathematical Background\n* Application examples\n\n## Repo structure\n\n```bash\n.\n├── bmm_multitask_learning  # python package\n├── docs\n├── examples                # notebooks with package applications\n├── LICENSE\n├── mkdocs.yml\n├── poetry.lock\n├── pyproject.toml\n├── README.md\n├── Sketch_Multitask_Learning.pdf   # blogpost about implemented algorithms\n└── tests\n```\n\n## Installation\n\nThe package uses *poetry* to manage dependencies and builds.\n\n### Via poetry\n\nIf you use poetry, you can add the package as your dependency\n\n```bash\npoetry add git+https://github.com/intsystems/bmm-multitask-learning.git\n```\n\n### Ready builds\n\nYou can download ready builds from [github](TODO:add release link).\n\n### Build from source\n\n```bash\ngit clone https://github.com/intsystems/bmm-multitask-learning.git\ncd bmm-multitask-learning\npoetry build -o build_dir\n```\n\nNow you can add generated package to your envirement.\n\n## Blog post\n\nCurrently available as [pdf](MTL_Blog_Post.pdf).\n\n## Team\n\n* Iryna Zabarianska\n* Ilgam Latypov\n* Alexander Terentyev\n* Kirill Semkin\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintsystems%2Fbmm-multitask-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintsystems%2Fbmm-multitask-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintsystems%2Fbmm-multitask-learning/lists"}