{"id":13958338,"url":"https://github.com/xidongbo/AITM","last_synced_at":"2025-07-20T23:31:01.103Z","repository":{"id":42529555,"uuid":"330844556","full_name":"xidongbo/AITM","owner":"xidongbo","description":"TensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework. Code for the paper accepted by KDD21: Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising. [https://arxiv.org/abs/2105.08489]","archived":false,"fork":false,"pushed_at":"2023-10-19T11:49:11.000Z","size":73,"stargazers_count":106,"open_issues_count":1,"forks_count":30,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-09T13:18:34.824Z","etag":null,"topics":[],"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/xidongbo.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":"2021-01-19T02:44:00.000Z","updated_at":"2024-07-14T11:56:18.000Z","dependencies_parsed_at":"2023-01-18T13:53:45.937Z","dependency_job_id":null,"html_url":"https://github.com/xidongbo/AITM","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/xidongbo%2FAITM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xidongbo%2FAITM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xidongbo%2FAITM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xidongbo%2FAITM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xidongbo","download_url":"https://codeload.github.com/xidongbo/AITM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226844975,"owners_count":17691137,"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":"2024-08-08T13:01:29.872Z","updated_at":"2024-11-28T01:31:42.339Z","avatar_url":"https://github.com/xidongbo.png","language":"Python","funding_links":[],"categories":["其他_推荐系统"],"sub_categories":["网络服务_其他"],"readme":"# AITM\nTensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework.  \nCode for the paper accepted by KDD21: \nModeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising.\n[https://arxiv.org/abs/2105.08489]\n\n# Note(New)\nRecently we reformatted the model code as ```AITM_standard.py```. If you want to run the model on multiple tasks (more than two), you can directly pass in the parameter ```--num_tasks``` in ```AITM_standard.py```. But you need to configure the ```config.csv``` file to specify the size of the feature dictionary.\n\n# Requirement\npython==3.6  \ntensorflow-gpu==1.10.1  \n\n# Dataset\nWe use the public Ali-CCP (Alibaba Click and Conversion Prediction) dataset. [https://tianchi.aliyun.com/datalab/dataSet.html?dataId=408].\n\nPlease download and unzip the dataset first.\n\nSplit the data to train/validation/test files to run the codes directly:\n```\npython process_public_dataset.py\n```\n\n# Example to run the model\n```\npython AITM.py --embedding_dim 5 --lr 1e-3 --early_stop 1 --lamda 1e-6 --prefix AITM --weight 0.6\n```\n\nThe instruction of commands has been clearly stated in the codes (see the parse_args function).\n\n\n# Reference\nIf you are interested in the code, please cite our paper:\n```\nXi D, Chen Z, Yan P, et al. Modeling the sequential dependence among audience multi-step conversions with multi-task learning in targeted display advertising[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \u0026 Data Mining. 2021: 3745-3755.\n```\nor in bibtex style:\n```\n@inproceedings{xi2021modeling,\n  title={Modeling the sequential dependence among audience multi-step conversions with multi-task learning in targeted display advertising},\n  author={Xi, Dongbo and Chen, Zhen and Yan, Peng and Zhang, Yinger and Zhu, Yongchun and Zhuang, Fuzhen and Chen, Yu},\n  booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \\\u0026 Data Mining},\n  pages={3745--3755},\n  year={2021}\n}\n```\n\n# Other unofficial implementations for reference:\n## A PyTorch implementation of multi-task recommendation models\n[https://github.com/easezyc/Multitask-Recommendation-Library]\n\nLast Update Date: Oct. 19, 2023 (UTC+8)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxidongbo%2FAITM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxidongbo%2FAITM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxidongbo%2FAITM/lists"}