{"id":21594093,"url":"https://github.com/ornl/ornl-hydragnn-graph-generative-models","last_synced_at":"2025-06-25T13:04:47.257Z","repository":{"id":261696074,"uuid":"876868744","full_name":"ORNL/ORNL-HydraGNN-graph-generative-models","owner":"ORNL","description":"Graph generative models using HydraGNN as neural network architecture","archived":false,"fork":false,"pushed_at":"2025-04-11T12:35:51.000Z","size":363,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-04-12T21:58:27.520Z","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":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ORNL.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-22T17:28:11.000Z","updated_at":"2025-04-11T12:35:54.000Z","dependencies_parsed_at":"2024-11-07T23:34:14.358Z","dependency_job_id":"4328face-3c83-45a3-a4cc-c2c708e059d4","html_url":"https://github.com/ORNL/ORNL-HydraGNN-graph-generative-models","commit_stats":null,"previous_names":["ornl/ornl-hydragnn-graph-generative-models"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ORNL/ORNL-HydraGNN-graph-generative-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2FORNL-HydraGNN-graph-generative-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2FORNL-HydraGNN-graph-generative-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2FORNL-HydraGNN-graph-generative-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2FORNL-HydraGNN-graph-generative-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ORNL","download_url":"https://codeload.github.com/ORNL/ORNL-HydraGNN-graph-generative-models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2FORNL-HydraGNN-graph-generative-models/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261879273,"owners_count":23223737,"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":"2024-11-24T17:15:59.878Z","updated_at":"2025-06-25T13:04:47.214Z","avatar_url":"https://github.com/ORNL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Diffusion Models on Graphs with HydraGNN \n This project builds on HydraGNN, leveraging its powerful GNN and ML utilities for training, testing, and model optimization. \n\n## Features\n* TBD\n\n## Quick Start\nClone the repo:\n\n```bash\ngit clone \u003ctbd\u003e\ncd \u003ctbd\u003e\n```\n\n### Install Dependencies:\nMake sure you have the HydraGNN environment set up:\n```bash\npip install -r requirements.txt\n```\n\n### Run Training:\n```bash\npython \u003ctbd\u003e\n```\n\n## How It Works\nHydraGNN integration: We utilize the operational utilities from HydraGNN, such as model training, testing, and optimization, to simplify workflow.\nDiffusion Process: Modeled on graph structures to simulate the propagation of information or features across the graph nodes. Perfect for dynamic systems! \nModel Parallelization: Thanks to HydraGNN, training large models with multi-GPU support is integrated.\n\n### ️Configuration\nAll model and training parameters can be easily set via our config.json file:\n\n```json\nmodel:\n  type: diffusion_gnn\n  layers: 5\n  hidden_dim: 128\ntrain:\n  epochs: 100\n  batch_size: 32\n  learning_rate: 0.001\n```\n\n## Modules\n`src/\u003c\u003e.py: `\n\n### Performance\nOur diffusion-enhanced GNNs show promising results in tasks such as:\n\n### Contributing\nWe welcome contributions! If you're interested in extending the diffusion model or improving performance, feel free to submit a pull request or open an issue. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fornl%2Fornl-hydragnn-graph-generative-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fornl%2Fornl-hydragnn-graph-generative-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fornl%2Fornl-hydragnn-graph-generative-models/lists"}