DeeProb-kit

DeeProb-kit is a unified library written in Python consisting of a collection of deep probabilistic models (DPMs) that are tractable and exact representations for the modelled probability distributions. The availability of a representative selection of DPMs in a single library makes it possible to combine them in a straightforward manner, a common practice in deep learning research nowadays. In addition, it includes efficiently implemented learning techniques, inference routines, statistical algorithms, and provides high-quality fully-documented APIs. The development of DeeProb-kit will help the community to accelerate research on DPMs as well as to standardise their evaluation and better understand how they are related based on their expressivity.

Features

• Inference algorithms for SPNs. [^1] [^4]
• Learning algorithms for SPNs structure. [^1] [^2] [^3] [^4] [^5]
• Chow-Liu Trees (CLT) as SPN leaves. [^13]
• Cutset Networks (CNets) with various learning criteria. [^12]
• Batch Expectation-Maximization (EM) for SPNs with arbitrarily leaves. [^14] [^15]
• Structural marginalization and pruning algorithms for SPNs.
• High-order moments computation for SPNs.
• JSON I/O operations for SPNs and CLTs. [^4]
• Plotting operations based on NetworkX for SPNs and CLTs. [^4]
• Randomized And Tensorized SPNs (RAT-SPNs). [^6]
• Deep Generalized Convolutional SPNs (DGC-SPNs). [^11]
• Masked Autoregressive Flows (MAFs). [^7]
• Real Non-Volume-Preserving (RealNVP) flows. [^8]
• Non-linear Independent Component Estimation (NICE) flows. [^9]

The collection of implemented models is summarized in the following table.

Installation

The library can be installed either from PIP repository or by source code.

# Install from PIP repository
pip install deeprob-kit

# Install from `main` git branch
pip install -e git+https://github.com/deeprob-org/deeprob-kit.git@main#egg=deeprob-kit

Project Directories

The documentation is generated automatically by Sphinx using sources stored in the docs directory.

A collection of code examples and experiments can be found in the examples and experiments directories respectively. Moreover, benchmark code can be found in the benchmark directory.

Cite

@misc{loconte2022deeprob,
  doi = {10.48550/ARXIV.2212.04403},
  url = {https://arxiv.org/abs/2212.04403},
  author = {Loconte, Lorenzo and Gala, Gennaro},
  title = {{DeeProb-kit}: a Python Library for Deep Probabilistic Modelling},
  publisher = {arXiv},
  year = {2022}
}

Related Repositories

• SPFlow
• RAT-SPN
• Random-PC
• LibSPN-Keras
• MAF
• RealNVP

References

[^1]: Peharz et al. On Theoretical Properties of Sum-Product Networks. AISTATS (2015). [^2]: Poon and Domingos. Sum-Product Networks: A New Deep Architecture. UAI (2011). [^3]: Molina, Vergari et al. Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains. AAAI (2018). [^4]: Molina, Vergari et al. SPFLOW : An easy and extensible library for deep probabilistic learning using Sum-Product Networks. CoRR (2019). [^5]: Di Mauro et al. Sum-Product Network structure learning by efficient product nodes discovery. AIxIA (2018). [^6]: Peharz et al. Probabilistic Deep Learning using Random Sum-Product Networks. UAI (2020). [^7]: Papamakarios et al. Masked Autoregressive Flow for Density Estimation. NeurIPS (2017). [^8]: Dinh et al. Density Estimation using RealNVP. ICLR (2017). [^9]: Dinh et al. NICE: Non-linear Independent Components Estimation. ICLR (2015). [^10]: Papamakarios, Nalisnick et al. Normalizing Flows for Probabilistic Modeling and Inference. JMLR (2021). [^11]: Van de Wolfshaar and Pronobis. Deep Generalized Convolutional Sum-Product Networks for Probabilistic Image Representations. PGM (2020). [^12]: Rahman et al. Cutset Networks: A Simple, Tractable, and Scalable Approach for Improving the Accuracy of Chow-Liu Trees. ECML-PKDD (2014). [^13]: Di Mauro, Gala et al. Random Probabilistic Circuits. UAI (2021). [^14]: Desana and Schnörr. Learning Arbitrary Sum-Product Network Leaves with Expectation-Maximization. CoRR (2016). [^15]: Peharz et al. Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits. ICML (2020).