{"id":20832410,"url":"https://github.com/ermongroup/hyperspn","last_synced_at":"2025-05-08T01:25:27.405Z","repository":{"id":104482563,"uuid":"413658554","full_name":"ermongroup/HyperSPN","owner":"ermongroup","description":"PyTorch implementation for \"HyperSPNs: Compact and Expressive Probabilistic Circuits\", NeurIPS 2021","archived":false,"fork":false,"pushed_at":"2021-10-26T03:02:58.000Z","size":18463,"stargazers_count":13,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-31T16:13:17.176Z","etag":null,"topics":["density-estimation","probabilistic-circuits","pytorch","regularization","sum-product-networks"],"latest_commit_sha":null,"homepage":"","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/ermongroup.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":"2021-10-05T03:16:30.000Z","updated_at":"2024-11-28T19:26:57.000Z","dependencies_parsed_at":"2023-06-09T06:45:23.287Z","dependency_job_id":null,"html_url":"https://github.com/ermongroup/HyperSPN","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/ermongroup%2FHyperSPN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2FHyperSPN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2FHyperSPN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ermongroup%2FHyperSPN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ermongroup","download_url":"https://codeload.github.com/ermongroup/HyperSPN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252980148,"owners_count":21835174,"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":["density-estimation","probabilistic-circuits","pytorch","regularization","sum-product-networks"],"created_at":"2024-11-18T00:11:45.434Z","updated_at":"2025-05-08T01:25:27.392Z","avatar_url":"https://github.com/ermongroup.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HyperSPN\n\nThis repository contains code for the paper:\n\nHyperSPNs: Compact and Expressive Probabilistic Circuits\n\n```\n\"HyperSPNs: Compact and Expressive Probabilistic Circuits\"\nAndy Shih, Dorsa Sadigh, Stefano Ermon\nIn Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021\n\n@inproceedings{ShihSEneurips21,\n  author    = {Andy Shih and Dorsa Sadigh and Stefano Ermon},\n  title     = {HyperSPNs: Compact and Expressive Probabilistic Circuits},\n  booktitle = {Advances in Neural Information Processing Systems 34 (NeurIPS)},\n  month     = {december},\n  year      = {2021},\n  keywords  = {conference}\n}\n```\n\n## Installation\n\n```\nconda env create -f environment.yml\n```\n\nOptionally, for EinsumNetworks:\n```\ncd EinsumNetworks\npip3 install -r requirements.txt\n```\n\n## Datasets and Repos\n\nThe Twenty Datasets benchmark is from [here](https://github.com/arranger1044/DEBD).\n\nThe Amazon Baby Registries benchmark is from [here](https://github.com/cgartrel/LowRankDPP.jl/tree/master/data/Amazon-baby-registry). The dataset was converted from the set format into the binary format.\n\nThe Einsum Network repository is from [here](https://github.com/cambridge-mlg/EinsumNetworks).\n\n\n## Commands\n\nExperiments can be launched with the helper bash files\n```\nrunid=0\nbash bashfiles/run_hyperspn.bash ${runid} 5\nbash bashfiles/run_hyperspn.bash ${runid} 10\nbash bashfiles/run_hyperspn.bash ${runid} 20\n\nbash bashfiles/run_spn.bash ${runid} 1e-3\nbash bashfiles/run_spn.bash ${runid} 1e-4\nbash bashfiles/run_spn.bash ${runid} 1e-5\n```\n\n```\ncd EinsumNetworks/src/\npython train_svhn_mixture.py --run=0\npython train_svhn_mixture.py --nn --run=0\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fermongroup%2Fhyperspn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fermongroup%2Fhyperspn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fermongroup%2Fhyperspn/lists"}