{"id":19321850,"url":"https://github.com/abductivelearning/abl_nc","last_synced_at":"2025-11-17T05:01:49.471Z","repository":{"id":88847663,"uuid":"570767254","full_name":"AbductiveLearning/ABL_nc","owner":"AbductiveLearning","description":null,"archived":false,"fork":false,"pushed_at":"2024-01-31T06:02:47.000Z","size":486,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-06T05:41:47.624Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AbductiveLearning.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2022-11-26T03:58:24.000Z","updated_at":"2024-01-17T03:41:02.000Z","dependencies_parsed_at":"2023-06-13T05:15:11.158Z","dependency_job_id":null,"html_url":"https://github.com/AbductiveLearning/ABL_nc","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/AbductiveLearning%2FABL_nc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbductiveLearning%2FABL_nc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbductiveLearning%2FABL_nc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AbductiveLearning%2FABL_nc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AbductiveLearning","download_url":"https://codeload.github.com/AbductiveLearning/ABL_nc/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240422999,"owners_count":19798862,"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":"2024-11-10T01:39:19.989Z","updated_at":"2025-11-17T05:01:44.435Z","avatar_url":"https://github.com/AbductiveLearning.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"🌟 **New!** [ABLkit](https://github.com/AbductiveLearning/ABLkit) released: A toolkit for Abductive Learning with high flexibility, user-friendly interface, and optimized performance. Welcome to try it out!🚀\n\n# Enabling Knowledge Refinement upon New Concepts in Abductive Learning\n\nThis is the repository for holding the sample code of [Enabling Knowledge Refinement upon New Concepts in Abductive Learning](https://www.lamda.nju.edu.cn/publication/aaai23ablnc.pdf)  in AAAI 2023.\n\nThis code is only tested in Linux environment.\n\n## Environment Dependency\n\n- Ubuntu 20.04\n- Python 3.8\n- Cuda 11.3\n- PyTorch\n- CuPy\n- clingo\n- tqdm\n- imblearn\n- pytod\n- scikit-learn\n- ILASP (https://doc.ilasp.com/installation.html)\n\nTo create the above environment with [Anaconda](https://www.anaconda.com/products/distribution), you can run the following command (cudatoolkit=11.3 for new GPUs / new drivers, cudatoolkit=10.1 for old GPUs):\n\n(cudatoolkit=11.3)\n\n```bash\nconda create -n ablnc python=3.8 -y\nconda activate ablnc\nconda install pytorch=1.12 torchvision torchaudio cudatoolkit=11.3 -c pytorch\npip install cupy-cuda11x clingo tqdm matplotlib imblearn pytod scikit-learn\nDownload and install ILASP according to https://doc.ilasp.com/installation.html and copy './ILASP' to current path\n```\n\n(cudatoolkit=10.1)\n\n```bash\nconda create -n ablnc python=3.8 -y\nconda activate ablnc\nconda install pytorch=1.7 torchvision torchaudio cudatoolkit=10.1 -c pytorch\npip install cupy-cuda101 clingo tqdm matplotlib imblearn pytod scikit-learn\nDownload and install ILASP according to https://doc.ilasp.com/installation.html and copy './ILASP' to current path\n```\n\n## Running Code\n\nTo reproduce the experiment results, we can simply run the following code:\n\n- Less-Than with New Digits\n\n  ```\n  python main.py --task=less_than\n  ```\n\n- Chess with New Pieces\n\n  ```\n  python main.py --task=chess\n  ```\n\n- Multiples of Three\n\n  ```\n  python main.py --task=multiples_of_three\n  ```\n\nTo view or change the hyperparameters, please refer to the *arg_init()* function in the code.\n\n## Reference\n\n```\n@inproceedings{ablnc2023huang,\n  title={Enabling Knowledge Refinement upon New Concepts in Abuctive Learning},\n  author={Huang, Yu-Xuan and Dai, Wang-Zhou and Jiang, Yuan and Zhou, Zhi-Hua},\n  booktitle={Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI'23)},\n  //pages={},\n  year={2023}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabductivelearning%2Fabl_nc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabductivelearning%2Fabl_nc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabductivelearning%2Fabl_nc/lists"}