{"id":19565124,"url":"https://github.com/graph-0/graphgdp","last_synced_at":"2026-03-05T01:33:35.347Z","repository":{"id":165828705,"uuid":"539791058","full_name":"GRAPH-0/GraphGDP","owner":"GRAPH-0","description":"Implementation for the paper: GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation","archived":false,"fork":false,"pushed_at":"2022-12-10T16:14:39.000Z","size":2041,"stargazers_count":27,"open_issues_count":2,"forks_count":7,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-27T00:33:09.854Z","etag":null,"topics":["diffusion-models","graph-generation"],"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/GRAPH-0.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-09-22T04:02:09.000Z","updated_at":"2025-04-15T13:33:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"0f987af2-f33f-4b55-ade1-02745de8d731","html_url":"https://github.com/GRAPH-0/GraphGDP","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GRAPH-0/GraphGDP","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GRAPH-0%2FGraphGDP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GRAPH-0%2FGraphGDP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GRAPH-0%2FGraphGDP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GRAPH-0%2FGraphGDP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GRAPH-0","download_url":"https://codeload.github.com/GRAPH-0/GraphGDP/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GRAPH-0%2FGraphGDP/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30104490,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T01:06:53.091Z","status":"ssl_error","status_checked_at":"2026-03-05T01:02:35.679Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["diffusion-models","graph-generation"],"created_at":"2024-11-11T05:25:08.828Z","updated_at":"2026-03-05T01:33:30.336Z","avatar_url":"https://github.com/GRAPH-0.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation\n\nOfficial Code Repository for GraphGDP (ICDM 2022).\n\n## Dependencies \n\nThe main requirements are:\n* pytorch 1.11\n* PyG 2.1\n* DGL 0.9.1 (for GIN-based metrics from GGM-metrics)\n\nOthers see requirements.txt .\n\n## Code Usage\n\n### Training Example\n1. Community small dataset\n```shell\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode train --workdir YOUR_PATH\n```\n\n2. Ego small dataset\n\n\n\n### Evaluation Example\n* EM method sampling \n```shell\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode eval --workdir YOUR_PATH \\\n--config.eval.begin_ckpt 150 --config.eval.end_ckpt 150\n```\n\n* Langevin correction\n```shell\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode eval --workdir YOUR_PATH \\\n--config.eval.begin_ckpt 150 --config.eval.end_ckpt 150 --config.sampling.corrector langevin --config.sampling.snr 0.20\n```\n\n* ODE Solvers\n```shell\n# scipy ODE (CPU)\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode eval --workdir YOUR_PATH \\\n--config.eval.begin_ckpt 150 --config.eval.end_ckpt 150 --config.sampling.method ode \\\n--config.sampling.rtol 1e-4 --config.sampling.atol 1e-4\n\n# Neural ODE (GPU) - Adaptive-step\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode eval --workdir YOUR_PATH \\\n--config.eval.begin_ckpt 150 --config.eval.end_ckpt 150 --config.sampling.method diffeq \\\n--config.sampling.ode_method dopri5 --config.sampling.rtol 1e-4 --config.sampling.atol 1e-4\n\n# Neural ODE (GPU) - Fixed-step\npython main.py --config configs/vp_com_small_pgsn.py --config.model.beta_max 5.0 --mode eval --workdir YOUR_PATH \\\n--config.eval.begin_ckpt 150 --config.eval.end_ckpt 150 --config.sampling.method diffeq \\\n--config.sampling.ode_method rk4 --config.sampling.ode_step 0.10\n```\n\n*Note*: we recommend training with config.model.beta_max 20.0 when utilizing probability flow ODEs.\n\nSome models and generated samples are provided on [Google Drive](https://drive.google.com/drive/folders/103eZR1JsPOXsJztP-RdXUHnoZqvOAOqh?usp=sharing).\n\n## Citation\n\n```bibtex\n@article{huang2022graphgdp,\n  title={GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation},\n  author={Huang, Han and Sun, Leilei and Du, Bowen and Fu, Yanjie and Lv, Weifeng},\n  journal={arXiv preprint arXiv:2212.01842},\n  year={2022}\n}\n```\n\n\n\n*Acknowledgement:* Our implementation is based on the repo [Score_SDE](https://github.com/yang-song/score_sde_pytorch). \nEvaluation implementation is modified from the repo [GGM-metrics](https://github.com/uoguelph-mlrg/GGM-metrics).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraph-0%2Fgraphgdp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgraph-0%2Fgraphgdp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraph-0%2Fgraphgdp/lists"}