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.

Model	Description
Binary-CLT	Binary Chow-Liu Tree (CLT)
Binary-CNet	Binary Cutset Network (CNet)
SPN	Vanilla Sum-Product Network
MSPN	Mixed Sum-Product Network
XPC	Random Probabilistic Circuit
RAT-SPN	Randomized and Tensorized Sum-Product Network
DGC-SPN	Deep Generalized Convolutional Sum-Product Network
MAF	Masked Autoregressive Flow
NICE	Non-linear Independent Components Estimation Flow
RealNVP	Real-valued Non-Volume-Preserving Flow

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}
}

References

1(1,2): Peharz et al. On Theoretical Properties of Sum-Product Networks. AISTATS (2015).
4(1,2,3,4): Molina, Vergari et al. SPFLOW : An easy and extensible library for deep probabilistic learning using Sum-Product Networks. CoRR (2019).
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).
5: Di Mauro et al. Sum-Product Network structure learning by efficient product nodes discovery. AIxIA (2018).
13: Di Mauro, Gala et al. Random Probabilistic Circuits. UAI (2021).
12: Rahman et al. Cutset Networks: A Simple, Tractable, and Scalable Approach for Improving the Accuracy of Chow-Liu Trees. ECML-PKDD (2014).
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).
6: Peharz et al. Probabilistic Deep Learning using Random Sum-Product Networks. UAI (2020).
11: Van de Wolfshaar and Pronobis. Deep Generalized Convolutional Sum-Product Networks for Probabilistic Image Representations. PGM (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).