用符号推理和动态剪枝提升知识图谱问答的准确率与速度
Neural-Symbolic Message Passing with Dynamic Pruning
- 结合神经网络与符号逻辑，无需训练即可处理任意逻辑查询
- 动态剪枝过滤变量节点间的噪声消息，提升答案准确性
- 推理速度比现有方法快2到150倍，适合需要快速响应的应用
在不完整知识图谱上进行复杂查询回答（CQA）是一项挑战性任务。现有基于消息传递的方法在负查询上表现不佳，无法解决查询图中变量节点间的噪声消息问题，且缺乏可解释性，需复杂数据和高资源训练。本文提出一种基于预训练神经链接预测器的神经符号消息传递（NSMP）框架。通过引入符号推理与模糊逻辑，NSMP可在无需训练的情况下泛化至任意一阶存在量词逻辑查询，并提供可解释答案。此外，我们设计了动态剪枝策略，有效过滤变量节点间的噪声消息。实验表明，NSMP性能优异。通过复杂度分析与实证验证，其推理时间显著优于当前最先进的神经符号方法，在所有查询类型上均实现2×至150×以上的加速。
原文摘要 · Abstract (English)
Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs) is a challenging task. Recently, a line of message-passing-based research has been proposed to solve CQA. However, they perform unsatisfactorily on negative queries and fail to address the noisy messages between variable nodes in the query graph. Moreover, they offer little interpretability and require complex query data and resource-intensive training. In this paper, we propose a Neural-Symbolic Message Passing (NSMP) framework based on pre-trained neural link predictors. By introducing symbolic reasoning and fuzzy logic, NSMP can generalize to arbitrary existential first order logic queries without requiring training while providing interpretable answers. Furthermore, we introduce a dynamic pruning strategy to filter out noisy messages between variable nodes. Experimental results show that NSMP achieves a strong performance. Additionally, through complexity analysis and empirical verification, we demonstrate the superiority of NSMP in inference time over the current state-of-the-art neural-symbolic method. Compared to this approach, NSMP demonstrates faster inference times across all query types on benchmark datasets, with speedup ranging from 2$\times$ to over 150$\times$.
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。