Neural Decision-Propagation for Answer Set Programming
This work addresses the scalability bottleneck of classical solvers in neuro-symbolic AI by introducing a neural approach to stable model computation.
The authors propose a new method for computing stable models in Answer Set Programming, called decision-propagation (DProp), and its differentiable extension Neural DProp (NDProp). NDProp achieves improved accuracy and scalability on neuro-symbolic benchmarks compared to existing approaches.
Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend the capabilities of ASP to real world domains, their reasoning pipelines depend on classical solvers, which is a bottleneck for scalability. To tackle this problem, we propose a new method to compute stable models, called decision-propagation (DProp), which alternates falsity decisions and truth propagations. Successful DProp computations are shown to capture the stable model semantics. We then develop Neural DProp (NDProp), a differentiable extension of DProp with neural computation for decisions and fuzzy evaluation for propagations. We evaluate the capabilities of NDProp for learning decision heuristics as well as neuro-symbolic integration, and compare it with existing neuro-symbolic approaches. The results show that NDProp can learn to efficiently compute stable models, and it improves accuracy and scalability on neuro-symbolic benchmarks.