pydpm 5.1.0

A python library focuses on constructing deep probabilistic models on GPU.

A python library focuses on constructing Deep Probabilistic Models (DPMs). Our developed Pydpm not only provides efficient distribution sampling functions on GPU, but also has included the implementations of existing popular DPMs.

Documentation | Paper [Arxiv] | Tutorials | Benchmarks | Examples |

News

:fire:A new version that does not depend on Pycuda has been released.

:fire:An abundance of professional learning materials on Deep Generative Models from the Ermom's group at Stanford University. (CS236 - Fall 2021)

:fire:A tutorial of DPMs has been uploaded by Prof. Wilker Aziz (University of Amsterdam).

Install

The current version of PyDPM can be installed under either Windows or Linux system with PyPI.

$ pip install pydpm

For Windows system, we recommed to install Visual Studio 2019 as the compiler equipped with CUDA 11.5 toolkit; For Linux system, we recommed to install the latest version of CUDA toolkit.

The enviroment for testing has been released for easily reproducing our results.

$ conda env create -f enviroment.yaml

Overview

The overview of the framework of PyDPM library can be roughly split into four sectors, specifically Sampler, Model, Evaluation, and Example modules, which have been illustrated as follows:

1. Sampler module includes both parts of the basic Distribution Sampler and the sophisticate Model Sampler, which can effectively accomplish the sampling requirements of these DPMs constructed on either CPU or GPU;
2. Model module contains a wide variety of classical and popular DPMs, which can be directly called as APIs in Python;
3. Evaluation module provides a DataLoader sub-module to process data samples in various forms, such as images, text, graphs etc., and also a Metric sub-module to comprehensively evaluate these DPMs after training;
4. Example module, for each DPM included in the Model module, we provides a corresponding code demo equipped with a detailed explanation in the official docs.

The workflow of applying PyDPM for downstream tasks, which can be splited into four steps as follows:

1. Device deployment of pyDPM can be choose as a platform with either CPU or GPU;
2. Mechasnisms of model training or testing includes either or both of Gibbs sampling and back propagation, implemented by pyDPM.sampler and pyTorch respecitveily;
3. Model categories in pyDPM mainly include Bayesian Probabilistic Model, Deep-Learning Probabilistic Models, and Hybrid Probabilistic Models;
4. Applications of DPMs has included Nature Language Processing (NLP), Graph Neural Network (GNN), and Recommendation System (RS) etc.

Model List

The Model module in pyDPM has included a wide variety of popular DPMs, which can be roughly split into several categories, including Bayesian Probabilistic Model, Deep-Learning Probabilistic Models, and Hybrid Probabilistic Models.

Bayesian Probabilistic Models

Probabilistic Model Name	Abbreviation	Paper Link
Latent Dirichlet Allocation	LDA	Blei et al., 2003
Poisson Factor Analysis	PFA	Zhou et al., 2012
Poisson Gamma Belief Network	PGBN	Zhou et al., 2015
Convolutional Poisson Factor Analysis	CPFA	Wang et al., 2019
Convolutional Poisson Gamma Belief Network	CPGBN	Wang et al., 2019
Factor Analysis	FA
Gaussian Mixed Model	GMM
Poisson Gamma Dynamical Systems	PGDS	Zhou et al., 2016
Deep Poisson Gamma Dynamical Systems	DPGDS	Guo et al., 2018
Dirichlet Belief Networks	DirBN	Zhao et al., 2018
Deep Poisson Factor Analysis	DPFA	Gan et al., 2015
Word Embeddings Deep Topic Model	WEDTM	Zhao et al., 2018
Multimodal Poisson Gamma Belief Network	MPGBN	Wang et al., 2018
Graph Poisson Gamma Belief Network	GPGBN	Wang et al., 2020

Deep-Learning Probabilistic Models

Probabilistic Model Name	Abbreviation	Paper Link
Restricted Boltzmann Machines	RBM	Hinton et al., 2010
Variational Autoencoder	VAE	Kingma et al., 2014
Generative Adversarial Network	GAN	Goodfellow et al., 2014
Density estimation using Real NVP	RealNVP (2d)	Dinh et al., 2017
Denoising Diffusion Probabilistic Models	DDPM	Ho et al., 2020
Density estimation using Real NVP	RealNVP (image)	Dinh et al., 2018
Conditional Variational Autoencoder	CVAE	Sohn et al., 2015
Deep Convolutional Generative Adversarial Networks	DCGAN	Radford et al., 2016
Wasserstein Generative Adversarial Networks	WGAN	Arjovsky et al., 2017
Information Maximizing Generative Adversarial Nets	InfoGAN	Xi Chen et al., 2016

Hybrid Probabilistic Models

Probabilistic Model Name	Abbreviation	Paper Link
Weibull Hybrid Autoencoding Inference	WHAI	Zhang et al., 2018
Weibull Graph Attention Autoencoder	WGAAE	Wang et al., 2020
Recurrent Gamma Belief Network	rGBN	Guo et al., 2020
Multimodal Weibull Variational Autoencoder	MWVAE	Wang et al., 2020
Sawtooth Embedding Topic Model	SawETM	Duan et al., 2021
TopicNet	TopicNet	Duan et al., 2021
Deep Coupling Embedding Topic Model	dc-ETM	Li et al., 2022
Topic Taxonomy Mining with Hyperbolic Embedding	HyperMiner	Xu et al., 2022
Knowledge Graph Embedding Topic Model	KG-ETM	Wang et al., 2022
Variational Edge Parition Model	VEPM	He et al., 2022
Generative Text Convolutional Neural Network	GTCNN	Wang et al., 2022

Deep Proabilistic Models planned to be built

:fire:Welcome to introduce classical or novel Deep Proabilistic Models for us.

Probabilistic Model Name	Abbreviation	Paper Link
Nouveau Variational Autoencoder	NVAE	Vahdat et al., 2020
flow-based Variational Autoencoder	f-VAE	Su et al., 2018
Score-Based Generative Models	SGM	Bortoli et al., 2022
Poisson Flow Generative Models	PFGM	Xu et al., 2022
Stable Diffusion	LDM	Rombach et al., 2022
Denoising Diffusion Implicit Models	DDIM	Song et al., 2022
Vector Quantized Diffusion	VQ-Diffusion	Tang et al., 2023
Vector Quantized Variational Autoencoder	VQ-VAE	Aaron van den Oord et al., 2017
Conditional Generative Adversarial Nets	cGAN	Mirza et al., 2014
Information Maximizing Variational Autoencoders	InfoVAE	zhao et al.,2017
Generative Flow	Glow	Kingama et al., 2018
Structured Denoising Diffusion Models in Discrete State-Spaces	DP3M	Austin et al., 2021

Usage

Example: a few code lines to quickly construct and evaluate a 3-layer Bayesian model named PGBN on GPU.

from pydpm.model import PGBN
from pydpm.metric import ACC

# create the model and deploy it on gpu or cpu
model = PGBN([128, 64, 32], device='gpu')
model.initial(train_data)
train_local_params = model.train(train_data, iter_all=100)
train_local_params = model.test(train_data, iter_all=100)
test_local_params = model.test(test_data, iter_all=100)

# evaluate the model with classification accuracy
# the demo accuracy can achieve 0.8549
results = ACC(train_local_params.Theta[0], test_local_params.Theta[0], train_label, test_label, 'SVM')

# save the model after training
model.save()

Example: a few code lines to quickly deploy distribution sampler of Pydpm on GPU.

from pydpm.sampler import Basic_Sampler

sampler = Basic_Sampler('gpu')
a = sampler.gamma(np.ones(100)*5, 1, times=10)
b = sampler.gamma(np.ones([100, 100])*5, 1, times=10)

Compare

Compare the distribution sampling efficiency of PyDPM with numpy:

Compare the distribution sampling efficiency of PyDPM with tensorflow and torch:

Compare the distribution sampling efficiency of PyDPM with CuPy and PyCUDA(used by pydpm v1.0):

Contact

License: Apache License Version 2.0

Contact: Chaojie Wang [e-mail], Wei Zhao [e-mail], Xinyang Liu [e-mail], Bufeng Ge [e-mail], Jiawen Wu [e-mail]

Copyright (c), 2020, Chaojie Wang, Wei Zhao, Xinyang Liu, Jiawen Wu, Jie Ren, Yewen Li, Wenchao Chen, Hao Zhang, Bo Chen and Mingyuan Zhou