{"id":13686424,"url":"https://github.com/lrjconan/GRAN","last_synced_at":"2025-05-01T09:31:47.013Z","repository":{"id":35801495,"uuid":"210967111","full_name":"lrjconan/GRAN","owner":"lrjconan","description":"Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019","archived":false,"fork":false,"pushed_at":"2023-08-03T03:21:22.000Z","size":7992,"stargazers_count":458,"open_issues_count":10,"forks_count":97,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-08-03T15:05:18.982Z","etag":null,"topics":["deep-generative-model","generative-model","graph-generation","graph-neural-networks","neurips-2019"],"latest_commit_sha":null,"homepage":"","language":"C++","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,"governance":null}},"created_at":"2019-09-26T00:44:58.000Z","updated_at":"2024-07-28T05:29:18.000Z","dependencies_parsed_at":"2022-09-25T04:22:29.057Z","dependency_job_id":"0a7bfdbc-b5a7-43f6-a1ef-99e24da764d0","html_url":"https://github.com/lrjconan/GRAN","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%2FGRAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FGRAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FGRAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lrjconan%2FGRAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lrjconan","download_url":"https://codeload.github.com/lrjconan/GRAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224250216,"owners_count":17280522,"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":["deep-generative-model","generative-model","graph-generation","graph-neural-networks","neurips-2019"],"created_at":"2024-08-02T15:00:32.178Z","updated_at":"2024-11-12T09:30:49.566Z","avatar_url":"https://github.com/lrjconan.png","language":"C++","funding_links":[],"categories":["C++"],"sub_categories":[],"readme":"\n# GRAN\n\nThis is the official PyTorch implementation of [Efficient Graph Generation with Graph Recurrent Attention Networks](https://arxiv.org/abs/1910.00760) as described in the following NeurIPS 2019 paper:\n\n```\n@inproceedings{liao2019gran,\n  title={Efficient Graph Generation with Graph Recurrent Attention Networks}, \n  author={Liao, Renjie and Li, Yujia and Song, Yang and Wang, Shenlong and Nash, Charlie and Hamilton, William L. and Duvenaud, David and Urtasun, Raquel and Zemel, Richard}, \n  booktitle={NeurIPS},\n  year={2019}\n}\n```\n\n## Visualization\n\n### Generation of GRAN per step:\n![](http://www.cs.toronto.edu/~rjliao/imgs/gran_model.gif)\n\n\n### Overall generation process:\n\u003cimg src=\"http://www.cs.toronto.edu/~rjliao/imgs/gran_generation.gif\" height=\"400px\" width=\"550px\" /\u003e\n\n\n## Dependencies\nPython 3, PyTorch(1.2.0)\n\nOther dependencies can be installed via \n\n  ```pip install -r requirements.txt```\n\n\n## Run Demos\n\n### Train\n* To run the training of experiment ```X``` where ```X``` is one of {```gran_grid```, ```gran_DD```, ```gran_DB```, ```gran_lobster```}:\n\n  ```python run_exp.py -c config/X.yaml```\n  \n\n**Note**:\n\n* Please check the folder ```config``` for a full list of configuration yaml files.\n* Most hyperparameters in the configuration yaml file are self-explanatory.\n\n### Test\n\n* After training, you can specify the ```test_model``` field of the configuration yaml file with the path of your best model snapshot, e.g.,\n\n  ```test_model: exp/gran_grid/xxx/model_snapshot_best.pth```\t\n\n* To run the test of experiments ```X```:\n\n  ```python run_exp.py -c config/X.yaml -t```\n\n**Note**:\n\n* Please check the [evaluation](https://github.com/JiaxuanYou/graph-generation) to set up.\n\n### Trained Models\n* You could use our trained model for comparisons. Please make sure you are using the same split of the dataset. Running the following script will download the trained model:\n\n\t```./download_model.sh```\t\n\n## Sampled Graphs from GRAN\n\n* Proteins Graphs from Training Set:\n![](http://www.cs.toronto.edu/~rjliao/imgs/protein_train.png)\n\n* Proteins Graphs Sampled from GRAN:\n![](http://www.cs.toronto.edu/~rjliao/imgs/protein_sample.png)\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%2FGRAN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flrjconan%2FGRAN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flrjconan%2FGRAN/lists"}