dPASP: A Comprehensive Differentiable Probabilistic Answer Set Programming Environment For Neurosymbolic Learning and Reasoning
This provides a tool for researchers and practitioners in AI to build sophisticated neuro-symbolic models with minimal deep learning expertise, though it appears incremental as it builds on existing probabilistic logic programming concepts.
The authors introduced dPASP, a differentiable probabilistic answer set programming framework for neuro-symbolic learning and reasoning, enabling the specification of models that integrate perception, reasoning, and statistical knowledge with gradient-based learning.
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.