{"id":19199851,"url":"https://github.com/rose-stl-lab/hierarchical-neural-processes","last_synced_at":"2025-05-09T01:28:46.313Z","repository":{"id":41113547,"uuid":"501527122","full_name":"Rose-STL-Lab/Hierarchical-Neural-Processes","owner":"Rose-STL-Lab","description":null,"archived":false,"fork":false,"pushed_at":"2023-06-13T00:41:45.000Z","size":111,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-03-31T20:35:14.601Z","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/Rose-STL-Lab.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,"publiccode":null,"codemeta":null}},"created_at":"2022-06-09T06:13:57.000Z","updated_at":"2025-03-03T11:46:42.000Z","dependencies_parsed_at":"2024-11-09T12:39:56.995Z","dependency_job_id":null,"html_url":"https://github.com/Rose-STL-Lab/Hierarchical-Neural-Processes","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/Rose-STL-Lab%2FHierarchical-Neural-Processes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FHierarchical-Neural-Processes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FHierarchical-Neural-Processes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FHierarchical-Neural-Processes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Rose-STL-Lab","download_url":"https://codeload.github.com/Rose-STL-Lab/Hierarchical-Neural-Processes/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253173632,"owners_count":21865724,"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":"2024-11-09T12:29:12.444Z","updated_at":"2025-05-09T01:28:46.292Z","avatar_url":"https://github.com/Rose-STL-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n## Multi-fidelity Hierarchical Neural Processes\n## Paper: \nDongxia Wu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu, [Multi-fidelity Hierarchical Neural Processes](https://arxiv.org/abs/2206.04872), \nKDD 2022\n\n## Abstract:\nScience and engineering fields use computer simulation extensively. These simulations are often run at multiple levels of sophistication to balance \naccuracy and efficiency. Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs. Cheap data generated \nfrom low-fidelity simulators can be combined with limited high-quality data generated by an expensive high-fidelity simulator. Existing methods based \non Gaussian processes rely on strong assumptions of the kernel functions and can hardly scale to high-dimensional settings. We propose Multi-fidelity \nHierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling. MF-HNP inherits the flexibility \nand scalability of Neural Processes. The latent variables transform the correlations among different fidelity levels from observations to latent space. \nThe predictions across fidelities are conditionally independent given the latent states. It helps alleviate the error propagation issue in existing \nmethods. MF-HNP is flexible enough to handle non-nested high dimensional data at different fidelity levels with varying input and output dimensions. \nWe evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation. \nIn contrast to deep Gaussian Processes with only low-dimensional (\u003c 10) tasks, our method shows great promise for speeding up high-dimensional \ncomplex simulations (over 7000 for epidemiology modeling and 45000 for climate modeling).\n\n## Requirements\n* torch\n* scipy\u003e=0.19.0\n* numpy\u003e=1.12.1\n* pandas\u003e=0.19.2\n* pyyaml\n* statsmodels\n* tensorflow\u003e=1.3.0\n* torch\n* tables\n* future\n* sklearn\n* matplotlib\n* gpytorch\n* math\n\nTo install requirements:\n```\npip install -r requirements.txt\n```\n## Neural Processes Model Training and Evaluation\n```\ncd sir_np/BA/*\npython train.py\ncd sir_np/MA/*\npython train.py\ncd climate_np/BA/*\npython train.py\ncd climate_np/MA/*\npython train.py\n```\n## Gaussian process Model Training and Evaluation\n```\ncd sir_gp\nrun *.ipynb\ncd climate_gp\nrun *.ipynb\n```\n\n## [Dataset](https://drive.google.com/drive/folders/1osXBkuDuzSmB8__2r3lLoOLHIXqju3G2?usp=sharing)\nFor Neural Processes Model, download sir_np/\\*/data to dataset_dir: sir_np/data/, download climate_np/\\*/data to dataset_dir: climate_np/data/  \nFor Gaussian process Model, download sir_gp/nargp_data to dataset_dir: sir_gp/, download sir_gp/sfgp_data to dataset_dir: sir_gp/, \ndownload climate_gp/* to dataset_dir: climate_gp/\n\n\n## Cite\n```\n@article{wu2022multi,\n  title={Multi-fidelity Hierarchical Neural Processes},\n  author={Wu, Dongxia and Chinazzi, Matteo and Vespignani, Alessandro and Ma, Yi-An and Yu, Rose},\n  journal={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery \\\u0026 Data Mining},\n  year={2022}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frose-stl-lab%2Fhierarchical-neural-processes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frose-stl-lab%2Fhierarchical-neural-processes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frose-stl-lab%2Fhierarchical-neural-processes/lists"}