神经查询模型未必比简单路径计数更优，两者互补性强。
Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
- 用放宽查询约束并计数路径的方式替代神经模型
- 多数据集测试显示神经与非神经方法性能接近
- 两者答案差异大，组合效果优于单一方法
当前神经复杂查询回答（CQA）模型被认为能超越图结构显式信息，实现泛化推理。本文通过系统分析，将神经模型与无需训练的查询松弛策略进行对比：后者通过放宽查询约束、统计路径数量来检索候选答案。在多个数据集和查询结构下，发现神经模型并未一致优于松弛方法，且两者答案重叠度极低。组合两者输出可稳定提升性能。结果表明，现有神经模型未能涵盖查询松弛所捕捉的推理模式，提示应重视非神经基线，并建议未来工作融合松弛机制。
原文摘要 · Abstract (English)
Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query processing. In this work, we critically examine this assumption through a systematic analysis comparing neural CQA models with an alternative, training-free query relaxation strategy that retrieves possible answers by relaxing query constraints and counting resulting paths. Across multiple datasets and query structures, we find several cases where neural and relaxation-based approaches perform similarly, with no neural model consistently outperforming the latter. Moreover, a similarity analysis reveals that their retrieved answers exhibit little overlap, and that combining their outputs consistently improves performance. These results call for a re-evaluation of progress in neural query answering: despite their complexity, current models fail to subsume the reasoning patterns captured by query relaxation. Our findings highlight the importance of stronger non-neural baselines and suggest that future neural approaches could benefit from incorporating principles of query relaxation.
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。