提出新框架统一符号与神经方法，高效准确回答知识图谱复杂查询
Exploring the Paradigm Shift from Grounding to Skolemization for Complex Query Answering on Knowledge Graphs
- 用可微分的斯科伦化模块和神经否定器构建联合架构
- 理论保证覆盖所有一类存在量词逻辑查询，计算开销极低
- 相比传统方法推理成本降低数个数量级，适合大规模知识图谱应用
在不完整知识图谱上进行复杂查询回答（CQA），通常形式化为带一个自由变量的存在量词一阶逻辑（EFO₁）推理，面临逻辑保真度与计算效率的根本权衡。本文建立‘归约’与‘斯科伦化’的二元分析框架，系统揭示此挑战并推动范式转变。虽然基于归约的方法固有组合爆炸问题，多数斯科伦化方法又未显式建模斯科伦函数，牺牲逻辑一致性。为此，我们提出逻辑约束向量符号架构（LVSA），一种神经符号框架，整合可微分斯科伦化模块、神经否定器及逻辑约束驱动的优化协议，协调几何与逻辑需求。理论上，LVSA对所有EFO₁查询具有通用性且计算复杂度低。实验证明，其性能优于现有斯科伦化方法，推理成本相较归约基线降低数个数量级。
原文摘要 · Abstract (English)
Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs), typically formalized as reasoning with Existential First-Order predicate logic with one free variable (EFO\textsubscript{1}), faces a fundamental tradeoff between logic fidelity and computational efficiency. This work establishes a Grounding-Skolemization dichotomy to systematically analyze this challenge and motivate a paradigm shift in CQA. While Grounding-based methods inherently suffer from combinatorial explosion, most Skolemization-based methods neglect to explicitly model Skolem functions and compromise logical consistency. To address these limitations, we propose the Logic-constrained Vector Symbolic Architecture (LVSA), a neuro-symbolic framework that unifies a differentiable Skolemization module and a neural negator, as well as a logical constraint-driven optimization protocol to harmonize geometric and logical requirements. Theoretically, LVSA guarantees universality for all EFO\textsubscript{1} queries with low computational complexity. Empirically, it outperforms state-of-the-art Skolemization-based methods and reduces inference costs by orders of magnitude compared to Grounding-based baselines.
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。