用超图建模表间结构，提升数据湖中可连接表发现的准确性和一致性。
HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery
- 构建超图融合表内与表间关系，用大模型增强表间连接表示。
- 在基准测试上，精度@15提升21.4%，召回@15提升17.2%。
- 适合数据湖管理、自动数据集成等场景，尤其关注结果的一致性。
作为数据湖管理中的关键任务，可连接表发现已受到广泛关注。现有基于语言模型的方法虽通过离线列表示学习与在线排序取得显著效果，但其设计未能充分考虑底层结构交互：(1) 离线阶段将表直接建模为孤立或成对列，难以捕捉丰富的表间与表内结构信息；(2) 在线阶段仅基于查询-候选相似度排序，忽略候选间的相互作用，导致结果集不连贯。为此，我们提出 HyperJoin，一种大语言模型（LLM）增强的超图框架，用于可连接表发现。具体而言，我们首先构建超图，利用表内超边与LLM增强的表间超边建模表。随后，将可连接表发现任务形式化为该超图上的链接预测问题。我们设计了HIN——层次化交互网络，通过列与超边间的双向消息传递学习丰富列表示。为增强结果列的一致性，我们将在线排序转化为保真度感知的top-k列选择问题，并引入重排序模块，采用最大生成树算法剔除噪声连接，最大化结果连贯性。实验表明，HyperJoin性能优于最优基线，平均提升21.4%（Precision@15）和17.2%（Recall@15）。
原文摘要 · Abstract (English)
As a pivotal task in data lake management, joinable table discovery has attracted widespread interest. While existing language model-based methods achieve remarkable performance by combining offline column representation learning with online ranking, their design insufficiently accounts for the underlying structural interactions: (1) offline, they directly model tables into isolated or pairwise columns, thereby struggling to capture the rich inter-table and intra-table structural information; and (2) online, they rank candidate columns based solely on query-candidate similarity, ignoring the mutual interactions among the candidates, leading to incoherent result sets. To address these limitations, we propose HyperJoin, a large language model (LLM)-augmented Hypergraph framework for Joinable table discovery. Specifically, we first construct a hypergraph to model tables using both the intra-table hyperedges and the LLM-augmented inter-table hyperedges. Consequently, the task of joinable table discovery is formulated as link prediction on this constructed hypergraph. We then design HIN, a Hierarchical Interaction Network that learns expressive column representations through bidirectional message passing over columns and hyperedges. To strengthen coherence and internal consistency in the result columns, we cast online ranking as a coherence-aware top-k column selection problem. We then introduce a reranking module that leverages a maximum spanning tree algorithm to prune noisy connections and maximize coherence. Experiments demonstrate the superiority of HyperJoin, achieving average improvements of 21.4% (Precision@15) and 17.2% (Recall@15) over the best baseline.
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。