{"id":13689479,"url":"https://github.com/lrjconan/RBP","last_synced_at":"2025-05-02T00:30:26.960Z","repository":{"id":41219050,"uuid":"140325139","full_name":"lrjconan/RBP","owner":"lrjconan","description":"Recurrent Back Propagation, Back Propagation Through Optimization, ICML 2018","archived":false,"fork":false,"pushed_at":"2019-01-12T02:09:58.000Z","size":4978,"stargazers_count":39,"open_issues_count":2,"forks_count":4,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-12T13:39:14.322Z","etag":null,"topics":["icml-2018","optimization","pytorch","rbp"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1803.06396","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/lrjconan.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":"2018-07-09T18:16:31.000Z","updated_at":"2024-07-17T14:52:32.000Z","dependencies_parsed_at":"2022-09-14T21:50:42.077Z","dependency_job_id":null,"html_url":"https://github.com/lrjconan/RBP","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/lrjconan%2FRBP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FRBP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FRBP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FRBP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lrjconan","download_url":"https://codeload.github.com/lrjconan/RBP/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251966431,"owners_count":21672666,"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":["icml-2018","optimization","pytorch","rbp"],"created_at":"2024-08-02T15:01:49.316Z","updated_at":"2025-05-02T00:30:23.984Z","avatar_url":"https://github.com/lrjconan.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# RBP\nThis is the PyTorch implementation of [Recurrent Back Propagation](https://arxiv.org/pdf/1803.06396.pdf) as described in the following ICML 2018 paper:\n\n```\n@article{liao2018reviving,\n  title={Reviving and Improving Recurrent Back-Propagation},\n  author={Liao, Renjie and Xiong, Yuwen and Fetaya, Ethan and Zhang, Lisa and Yoon, KiJung and Pitkow, Xaq and Urtasun, Raquel and Zemel, Richard},\n  journal={arXiv preprint arXiv:1803.06396},\n  year={2018}\n}\n```\n\n## Setup\nTo set up experiments, we need to build our customized operators by running the following scripts:\n```\n./setup.sh\n``` \n\n## Dependencies\nPython 3, PyTorch(0.4.0)\n\n\n## Run Demos\n* To run experiments ```X``` where ```X``` is one of {```hopfield```, ```cora```, ```pubmed```, ```hypergrad```}:\n\n  ```python run_exp.py -c config/X.yaml```\n  \n\n**Notes**:\n* Most hyperparameters in the configuration yaml file are self-explanatory.\n* To switch between BPTT, TBPTT and RBP variants, you need to specify ```grad_method``` in the config file.\n* Conjugate gradient based RBP requires support of forward mode auto-differentiation which we only provided for the experiments of Hopfield networks and graph neural networks (GNNs). You can check the comments in ```model/rbp.py``` for more details.\n\n## Cite\nPlease cite our paper if you use this code in your research work.\n\n## Questions/Bugs\nPlease submit a Github issue or contact rjliao@cs.toronto.edu if you have any questions or find any bugs.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flrjconan%2FRBP","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flrjconan%2FRBP","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flrjconan%2FRBP/lists"}