{"id":18478760,"url":"https://github.com/facebookresearch/adatt","last_synced_at":"2025-04-08T15:32:55.293Z","repository":{"id":172572971,"uuid":"648832878","full_name":"facebookresearch/AdaTT","owner":"facebookresearch","description":"pytorch open-source library for the paper \"AdaTT Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations\"","archived":false,"fork":false,"pushed_at":"2024-08-09T04:17:17.000Z","size":19,"stargazers_count":46,"open_issues_count":0,"forks_count":8,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-23T16:01:34.629Z","etag":null,"topics":["moe","mtl","multitask-learning"],"latest_commit_sha":null,"homepage":"","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/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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}},"created_at":"2023-06-03T00:01:08.000Z","updated_at":"2025-03-21T06:04:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"abc3deb4-d1b4-427d-8188-bee17f48c598","html_url":"https://github.com/facebookresearch/AdaTT","commit_stats":null,"previous_names":["facebookresearch/adatt"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FAdaTT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FAdaTT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FAdaTT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FAdaTT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/AdaTT/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247871586,"owners_count":21010064,"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":["moe","mtl","multitask-learning"],"created_at":"2024-11-06T12:11:43.113Z","updated_at":"2025-04-08T15:32:54.929Z","avatar_url":"https://github.com/facebookresearch.png","language":"Python","readme":"# AdaTT\n\nWelcome to the AdaTT repository! This repository provides a PyTorch library for multitask learning, specifically focused on the models evaluated in the paper [\"AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations\" (KDD'23)\"](https://doi.org/10.1145/3580305.3599769).\n\n[**[arXiv]**](https://arxiv.org/abs/2304.04959)    [**[slides]**](https://drive.google.com/file/d/1I8XpxPxwhP9KXuztEguYkuMM10kiJDS7/view?usp=sharing)\n\n## Models\n\nThis repository implements the following models:\n\n+ AdaTT [[Paper]](https://doi.org/10.1145/3580305.3599769)\n+ MMoE [[Paper]](https://dl.acm.org/doi/10.1145/3219819.3220007)\n+ Multi-level MMoE (an extension of MMoE)\n+ PLE [[Paper]](https://doi.org/10.1145/3383313.3412236)\n+ Cross-stitch [[Paper]](https://openaccess.thecvf.com/content_cvpr_2016/papers/Misra_Cross-Stitch_Networks_for_CVPR_2016_paper.pdf)\n+ Shared-bottom [[Paper]](https://link.springer.com/article/10.1023/a:1007379606734)\n\nTo facilitate the integration and selection of these models, we have implemented a class called `CentralTaskArch`.\n\n## License\n\nAdaTT is MIT-licensed.\n\n## Citation\n\nIf you find AdaTT's paper or code helpful, please consider citing:\n```\n@article{li2023adatt,\n  title={AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations},\n  author={Li, Danwei and Zhang, Zhengyu and Yuan, Siyang and Gao, Mingze and Zhang, Weilin and Yang, Chaofei and Liu, Xi and Yang, Jiyan},\n  journal={arXiv preprint arXiv:2304.04959},\n  year={2023}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fadatt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2Fadatt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fadatt/lists"}