HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery

2026-01-03

arXiv.org

AI Summary

This work addresses the limitations of existing table discovery methods, which struggle to effectively model both intra-table structure and complex inter-table relationships, and often yield inconsistent results due to online ranking strategies that ignore interactions among candidate columns. To overcome these challenges, the paper introduces a novel hypergraph-based formulation that captures table structure through intra-table hyperedges and enhances cross-table connections using large language model (LLM)-augmented hyperedges, reframing the task as hypergraph link prediction. A hierarchical interaction network is employed to learn column representations, complemented by a consistency-aware top-k column selection strategy and a maximum spanning tree–based reranking mechanism. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art baselines, achieving average improvements of 21.4% in Precision@15 and 17.2% in Recall@15.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Information Extraction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• joinable table discovery
• hypergraph
• link prediction
• structural interaction
• coherence

Innovation

• Hypergraph
• Large Language Model (LLM)
• Link Prediction
• Hierarchical Interaction Network
• Coherence-aware Ranking