用神经网络加速答案集编程的稳定模型计算，提升可扩展性。
Neural Decision-Propagation for Answer Set Programming
- 提出决策传播法，交替进行真假判断与传播推理
- 神经版方法在基准测试中提升准确率与计算效率
- 适合研究神经符号系统或需要高效逻辑推理的场景
将答案集编程（ASP）与神经网络结合是神经符号人工智能的前沿方向。现有方法虽拓展了ASP在现实场景的应用，但依赖传统求解器，难以规模化。为此，本文提出决策传播（DProp）方法，通过交替进行假值决策与真值传播来计算稳定模型，其计算过程能正确捕获稳定模型语义。进一步提出神经决策传播（NDProp），采用神经网络进行决策、模糊评估实现传播，具备可微特性。实验表明，NDProp能有效学习决策启发式，并在神经符号基准上显著提升准确率与可扩展性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。