Research

Paper

TESTING February 19, 2026

A Locality Radius Framework for Understanding Relational Inductive Bias in Database Learning

Authors

Aadi Joshi, Kavya Bhand

Abstract

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.

Metadata

arXiv ID: 2602.17092
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17092v1</id>\n    <title>A Locality Radius Framework for Understanding Relational Inductive Bias in Database Learning</title>\n    <updated>2026-02-19T05:31:03Z</updated>\n    <link href='https://arxiv.org/abs/2602.17092v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17092v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-02-19T05:31:03Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Aadi Joshi</name>\n    </author>\n    <author>\n      <name>Kavya Bhand</name>\n    </author>\n  </entry>"
}