提出局部半径概念，揭示关系推理深度与任务需求的匹配关系。
A Locality Radius Framework for Understanding Relational Inductive Bias in Database Learning
- 用局部半径衡量关系模式中预测所需的最小结构范围
- 发现模型性能取决于任务局部半径与网络聚合深度的匹配度
- 适用于数据库结构学习、图神经网络设计等场景
外键发现与相关模式级预测任务常使用图神经网络（GNN）建模，隐含假设关系归纳偏置能提升性能。然而，多跳结构推理是否真正必要仍不明确。本文提出局部半径（locality radius），作为确定关系模式中预测所需最小结构邻域的正式度量。我们假设模型性能关键取决于任务局部半径与架构聚合深度之间的对齐程度。通过在多个任务上开展受控实证研究——包括外键预测、连接代价估计、爆炸半径回归、级联影响分类及其它基于图的模式任务——并进行多种子实验、容量匹配比较、统计显著性检验、缩放分析和合成的半径可控基准测试，结果揭示出一致的偏置-半径对齐效应。
原文摘要 · Abstract (English)
Foreign key discovery and related schema-level prediction tasks are often modeled using graph neural networks (GNNs), implicitly assuming that relational inductive bias improves performance. However, it remains unclear when multi-hop structural reasoning is actually necessary. In this work, we introduce locality radius, a formal measure of the minimum structural neighborhood required to determine a prediction in relational schemas. We hypothesize that model performance depends critically on alignment between task locality radius and architectural aggregation depth. We conduct a controlled empirical study across foreign key prediction, join cost estimation, blast radius regression, cascade impact classification, and additional graph-derived schema tasks. Our evaluation includes multi-seed experiments, capacity-matched comparisons, statistical significance testing, scaling analysis, and synthetic radius-controlled benchmarks. Results reveal a consistent bias-radius alignment effect.
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。