dPASP: A Comprehensive Differentiable Probabilistic Answer Set Programming Environment For Neurosymbolic Learning and Reasoning

TL;DR

dPASP is a new differentiable probabilistic logic programming framework that integrates neural predicates, logic constraints, and probabilistic choices for neuro-symbolic reasoning, enabling end-to-end training of complex models.

Contribution

It introduces a comprehensive declarative environment for neuro-symbolic learning combining probabilistic logic, neural predicates, and multiple semantics for flexible reasoning.

Findings

Supports models combining perception, reasoning, and statistical knowledge.

Enables gradient-based learning with neural predicates and probabilistic choices.

Provides an implementation with inference and learning capabilities.

Abstract

We present dPASP, a novel declarative probabilistic logic programming framework for differentiable neuro-symbolic reasoning. The framework allows for the specification of discrete probabilistic models with neural predicates, logic constraints and interval-valued probabilistic choices, thus supporting models that combine low-level perception (images, texts, etc), common-sense reasoning, and (vague) statistical knowledge. To support all such features, we discuss the several semantics for probabilistic logic programs that can express nondeterministic, contradictory, incomplete and/or statistical knowledge. We also discuss how gradient-based learning can be performed with neural predicates and probabilistic choices under selected semantics. We then describe an implemented package that supports inference and learning in the language, along with several example programs. The package requires minimal user knowledge of deep learning system's inner workings, while allowing end-to-end training of rather sophisticated models and loss functions.