arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2512.02444cs.DBcs.LG
收藏

QJoin: 基于强化学习的变换感知可连接数据发现

MetaJoin: Adaptive Join Selections for Heterogeneous Tables

Cornell University(康奈尔大学)

Ning Wang, Sainyam Galhotra

AI总结:

QJoin通过强化学习框架学习并重用变换策略,提升连接发现的准确性和效率。

摘要:

在大规模、异构的数据仓库中发现哪些表可以连接以及通过何种变换进行连接是数据集成和数据发现中的核心挑战。传统的连接发现方法大多针对等值连接,假设连接键完全或近似匹配。这些技术虽然在干净、规范化良好的数据库中效率高,但在开放或联邦设置中表现不佳,因为标识符格式不一致、嵌套或分散在多个列中。近似或模糊连接可以缓解轻微的字符串变化,但无法捕捉系统性的变换。我们引入QJoin,一种基于强化学习的框架,能够学习并在连接任务中重用变换策略。QJoin在具有唯一性意识的奖励下训练代理,平衡相似性与键的多样性,使其能够探索简洁、高价值的变换链。为加速新连接,我们引入两种重用机制:(i) 代理迁移,通过预训练代理初始化新策略;(ii) 变换重用,缓存成功操作序列以供相似列簇使用。在AutoJoin Web基准测试(31张表对)上,QJoin实现了平均F1分数为91.0%。对于NYC+芝加哥开放数据集中的19,990个连接任务,QJoin通过重用将运行时间减少高达7.4%(13,747秒)。这些结果表明,变换学习和重用可以使得连接发现更加准确和高效。

英文摘要:

Joining heterogeneous tables requires different forms of correspondence, including exact agreement, syntactic transformation, semantic similarity, and entity-level matching. The appropriate join method is often unknown in advance, while running every candidate method incurs unnecessary cost. We introduce MetaJoin, a label-free framework for adaptive join selection. MetaJoin uses input evidence to choose an initial specialist, then uses specialist-specific output evidence to determine whether that result should be retained, compared with an alternative, escalated, or repaired. This allows join selection to adapt after execution rather than committing to a one-shot routing decision. We also introduce MNN Join, a transformation specialist that searches for string transformations by maximizing mutual-nearest-neighbor coverage between two unaligned columns and uses the same reciprocal structure to validate its output. We evaluate MetaJoin on 670 datasets from six benchmarks. It achieves 0.817 macro row-F1, slightly exceeding a benchmark-level oracle that is given the best standalone specialist for each benchmark (0.812), and outperforms label-free selection policies built from the same specialist portfolio by more than 0.13. Across the 609 datasets in the four transformation-dominant benchmarks, MNN Join outperforms every evaluated transformation baseline. Finally, MetaJoin's accuracy varies by only 0.015 as the controller backbone ranges from 3B to 14B parameters, showing that output validation and repair substantially reduce dependence on the initial routing decision.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑