SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks

TL;DR

SPFlow is an open-source Python library that simplifies the creation, inference, and learning of Sum-Product Networks, enabling efficient probabilistic modeling and extensibility for deep probabilistic learning tasks.

Contribution

It provides a user-friendly, extensible framework for deep probabilistic models, integrating various algorithms and enabling fast computation through compilation to hardware-specific code.

Findings

Supports quick creation of SPNs from data and DSL

Implements efficient inference routines like marginals and MPEs

Allows compilation into TensorFlow, C, CUDA, or FPGA for speed

Abstract

We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs). The library allows one to quickly create SPNs both from data and through a domain specific language (DSL). It efficiently implements several probabilistic inference routines like computing marginals, conditionals and (approximate) most probable explanations (MPEs) along with sampling as well as utilities for serializing, plotting and structure statistics on an SPN. Moreover, many of the algorithms proposed in the literature to learn the structure and parameters of SPNs are readily available in SPFlow. Furthermore, SPFlow is extremely extensible and customizable, allowing users to promptly distill new inference and learning routines by injecting custom code into a lightweight functional-oriented API framework. This is achieved in SPFlow by keeping an internal Python representation of the graph structure that also enables practical compilation of an SPN into a TensorFlow graph, C, CUDA or FPGA custom code, significantly speeding-up computations.