{"id":13784772,"url":"https://github.com/deeprob-org/deeprob-kit","last_synced_at":"2025-05-11T20:31:12.048Z","repository":{"id":45558270,"uuid":"410852413","full_name":"deeprob-org/deeprob-kit","owner":"deeprob-org","description":"A Python Library for Deep Probabilistic Modeling","archived":false,"fork":false,"pushed_at":"2024-10-25T17:12:43.000Z","size":330,"stargazers_count":60,"open_issues_count":5,"forks_count":9,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-11T19:17:16.278Z","etag":null,"topics":["normalizing-flows","probabilistic-circuits","probabilistic-models","sum-product-networks"],"latest_commit_sha":null,"homepage":"https://deeprob-kit.readthedocs.io/en/latest/","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/deeprob-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"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":"2021-09-27T11:13:38.000Z","updated_at":"2025-03-01T23:13:05.000Z","dependencies_parsed_at":"2025-04-11T19:17:18.285Z","dependency_job_id":"cb7d1273-d29f-40a8-a2fc-4e71c2d1fa87","html_url":"https://github.com/deeprob-org/deeprob-kit","commit_stats":{"total_commits":92,"total_committers":3,"mean_commits":"30.666666666666668","dds":0.07608695652173914,"last_synced_commit":"76ece3384d6b8ef96cede8bef4e5f3e590129992"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deeprob-org%2Fdeeprob-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deeprob-org%2Fdeeprob-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deeprob-org%2Fdeeprob-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deeprob-org%2Fdeeprob-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/deeprob-org","download_url":"https://codeload.github.com/deeprob-org/deeprob-kit/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253631941,"owners_count":21939368,"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":["normalizing-flows","probabilistic-circuits","probabilistic-models","sum-product-networks"],"created_at":"2024-08-03T19:00:52.274Z","updated_at":"2025-05-11T20:31:11.595Z","avatar_url":"https://github.com/deeprob-org.png","language":"Python","funding_links":[],"categories":["🧑‍💻 Repos \u003csmall\u003e(18)\u003c/small\u003e"],"sub_categories":["\u003cimg src=\"assets/pytorch.svg\" alt=\"PyTorch\" height=\"20px\"\u003e \u0026nbsp;PyTorch Repos"],"readme":"\u003e [!WARNING]\n\u003e This repository is deprecated in favour of the [cirkit](https://github.com/april-tools/cirkit) framework. Please have a look at it for your project.\n\u003e\n\n[![MIT license](https://img.shields.io/badge/License-MIT-blue.svg)](https://lbesson.mit-license.org/)\n[![PyPI version](https://badge.fury.io/py/deeprob-kit.svg)](https://badge.fury.io/py/deeprob-kit)\n[![codecov](https://codecov.io/gh/deeprob-org/deeprob-kit/branch/main/graph/badge.svg?token=4ZDC22QYEJ)](https://codecov.io/gh/deeprob-org/deeprob-kit)\n[![Continuous Integration](https://github.com/deeprob-org/deeprob-kit/actions/workflows/ci.yml/badge.svg)](https://github.com/deeprob-org/deeprob-kit/actions/workflows/ci.yml)\n[![Documentation Status](https://readthedocs.org/projects/deeprob-kit/badge/?version=latest)](https://deeprob-kit.readthedocs.io/en/latest/?badge=latest)\n\n![Logo](docs/source/deeprob-logo.svg)\n\n# DeeProb-kit\n\nDeeProb-kit is a unified library written in Python consisting of a collection of deep probabilistic models (DPMs) that\nare tractable and exact representations for the modelled probability distributions. The availability of a representative\nselection of DPMs in a single library makes it possible to combine them in a straightforward manner, a common practice\nin deep learning research nowadays. In addition, it includes efficiently implemented learning techniques, inference\nroutines, statistical algorithms, and provides high-quality fully-documented APIs. The development of DeeProb-kit will\nhelp the community to accelerate research on DPMs as well as to standardise their evaluation and better understand how\nthey are related based on their expressivity. \n\n## Features\n\n- Inference algorithms for SPNs. [^1] [^4]\n- Learning algorithms for SPNs structure. [^1] [^2] [^3] [^4] [^5]\n- Chow-Liu Trees (CLT) as SPN leaves. [^13]\n- Cutset Networks (CNets) with various learning criteria. [^12]\n- Batch Expectation-Maximization (EM) for SPNs with arbitrarily leaves. [^14] [^15]\n- Structural marginalization and pruning algorithms for SPNs.\n- High-order moments computation for SPNs.\n- JSON I/O operations for SPNs and CLTs. [^4]\n- Plotting operations based on NetworkX for SPNs and CLTs. [^4]\n- Randomized And Tensorized SPNs (RAT-SPNs). [^6]\n- Deep Generalized Convolutional SPNs (DGC-SPNs). [^11]\n- Masked Autoregressive Flows (MAFs). [^7]\n- Real Non-Volume-Preserving (RealNVP) flows. [^8]\n- Non-linear Independent Component Estimation (NICE) flows. [^9]\n\nThe collection of implemented models is summarized in the following table.\n\n| Model       | Description                                        |\n|-------------|----------------------------------------------------|\n| Binary-CLT  | Binary Chow-Liu Tree (CLT)                         |\n| Binary-CNet | Binary Cutset Network (CNet)                       |\n| SPN         | Vanilla Sum-Product Network                        |\n| MSPN        | Mixed Sum-Product Network                          |\n| XPC         | Random Probabilistic Circuit                       |\n| RAT-SPN     | Randomized and Tensorized Sum-Product Network      |\n| DGC-SPN     | Deep Generalized Convolutional Sum-Product Network |\n| MAF         | Masked Autoregressive Flow                         |\n| NICE        | Non-linear Independent Components Estimation Flow  |\n| RealNVP     | Real-valued Non-Volume-Preserving Flow             |\n\n## Installation\n\nThe library can be installed either from PIP repository or by source code.\n```shell\n# Install from PIP repository\npip install deeprob-kit\n```\n```shell\n# Install from `main` git branch\npip install -e git+https://github.com/deeprob-org/deeprob-kit.git@main#egg=deeprob-kit\n```\n\n## Project Directories\n\nThe documentation is generated automatically by Sphinx using sources stored in the [docs](docs) directory.\n\nA collection of code examples and experiments can be found in the [examples](examples) and [experiments](experiments)\ndirectories respectively.\nMoreover, benchmark code can be found in the [benchmark](benchmark) directory.\n\n## Cite\n\n```\n@misc{loconte2022deeprob,\n  doi = {10.48550/ARXIV.2212.04403},\n  url = {https://arxiv.org/abs/2212.04403},\n  author = {Loconte, Lorenzo and Gala, Gennaro},\n  title = {{DeeProb-kit}: a Python Library for Deep Probabilistic Modelling},\n  publisher = {arXiv},\n  year = {2022}\n}\n```\n\n## Related Repositories\n\n- [SPFlow](https://github.com/SPFlow/SPFlow)\n- [RAT-SPN](https://github.com/cambridge-mlg/RAT-SPN)\n- [Random-PC](https://github.com/gengala/Random-Probabilistic-Circuits)\n- [LibSPN-Keras](https://github.com/pronobis/libspn-keras)\n- [MAF](https://github.com/gpapamak/maf)\n- [RealNVP](https://github.com/chrischute/real-nvp)\n\n## References\n\n[^1]: Peharz et al. [*On Theoretical Properties of Sum-Product Networks*](http://proceedings.mlr.press/v38/peharz15.pdf). AISTATS (2015).\n[^2]: Poon and Domingos. [*Sum-Product Networks: A New Deep Architecture*](https://arxiv.org/pdf/1202.3732.pdf). UAI (2011).\n[^3]: Molina, Vergari et al. [*Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains*](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/16865/16619). AAAI (2018).\n[^4]: Molina, Vergari et al. [*SPFLOW : An easy and extensible library for deep probabilistic learning using Sum-Product Networks*](https://arxiv.org/pdf/1901.03704.pdf). CoRR (2019).\n[^5]: Di Mauro et al. [*Sum-Product Network structure learning by efficient product nodes discovery*](http://www.di.uniba.it/~ndm/pubs/dimauro18ia.pdf). AIxIA (2018).\n[^6]: Peharz et al. [*Probabilistic Deep Learning using Random Sum-Product Networks*](http://proceedings.mlr.press/v115/peharz20a/peharz20a.pdf). UAI (2020). \n[^7]: Papamakarios et al. [*Masked Autoregressive Flow for Density Estimation*](https://proceedings.neurips.cc/paper/2017/file/6c1da886822c67822bcf3679d04369fa-Paper.pdf). NeurIPS (2017).\n[^8]: Dinh et al. [*Density Estimation using RealNVP*](https://arxiv.org/pdf/1605.08803v3.pdf). ICLR (2017).\n[^9]: Dinh et al. [*NICE: Non-linear Independent Components Estimation*](https://arxiv.org/pdf/1410.8516.pdf). ICLR (2015).\n[^10]: Papamakarios, Nalisnick et al. [*Normalizing Flows for Probabilistic Modeling and Inference*](https://www.jmlr.org/papers/volume22/19-1028/19-1028.pdf). JMLR (2021).\n[^11]: Van de Wolfshaar and Pronobis. [*Deep Generalized Convolutional Sum-Product Networks for Probabilistic Image Representations*](http://proceedings.mlr.press/v138/wolfshaar20a/wolfshaar20a.pdf). PGM (2020).\n[^12]: Rahman et al. [*Cutset Networks: A Simple, Tractable, and Scalable Approach for Improving the Accuracy of Chow-Liu Trees*](https://link.springer.com/content/pdf/10.1007%2F978-3-662-44851-9_40.pdf). ECML-PKDD (2014).\n[^13]: Di Mauro, Gala et al. [*Random Probabilistic Circuits*](https://openreview.net/pdf?id=xzn1RVTCyB). UAI (2021).\n[^14]: Desana and Schnörr. [*Learning Arbitrary Sum-Product Network Leaves with Expectation-Maximization*](https://arxiv.org/pdf/1604.07243.pdf). CoRR (2016).\n[^15]: Peharz et al. [*Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits*](http://proceedings.mlr.press/v119/peharz20a/peharz20a.pdf). ICML (2020).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeprob-org%2Fdeeprob-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeeprob-org%2Fdeeprob-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeeprob-org%2Fdeeprob-kit/lists"}