MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery

2026-07-23

AI Summary

This work addresses the challenge of identifying joinable columns in data lakes and open data warehouses, where semantically equivalent but syntactically divergent values evade detection by traditional equality joins, and existing semantic join methods struggle to balance accuracy with scalability. To overcome this, the paper proposes a value-level join discovery approach based on compact semantic sketches. The method employs a novel sketching mechanism to approximate column pair joinability without exhaustive pairwise value comparisons and introduces a query sub-sampling operator with theoretical accuracy guarantees. Notably, it achieves substantial efficiency gains without requiring model training or fine-tuning. Experimental results demonstrate consistent superiority over state-of-the-art techniques across all benchmarks, with speedups up to 66× over other value-level methods, enabling efficient processing of columns containing up to 57K query values and 1M data lake values.

Abstract

Join discovery is a core task in dataset search, enabling users to find columns that can be joined with a given query column. Early approaches focused on equi-joins, but data lakes and open-data repositories often contain columns whose values refer to the same entity but use different syntactic representations. To address this challenge, recent approaches discover semantically joinable columns but face a fundamental trade-off: methods that perform value-level comparisons accurately identify joinable columns but scale poorly to columns with high cardinality; column-level methods that encode an entire column into a single embedding are efficient but do not capture the fine-grained value alignment that determines whether a join is possible. We present MosaicJoin, a value-level semantic join discovery method that balances this trade-off. MosaicJoin achieves scalability through a novel sketching strategy that approximates the joinability of a column pair without having to compare all values. At query time, MosaicJoin scores each candidate sketch using a joinability score at a cost bounded by the sketch size, making retrieval efficient even for high-cardinality columns. A query subsampling operator further reduces online search time with provable accuracy guarantees, enabling robust retrieval for large query columns. Extensive experiments show that MosaicJoin outperforms previously published methods across all benchmarks while running up to 66 times faster than other value-level methods. MosaicJoin requires no training or fine-tuning, and it scales robustly to query columns containing up to 57K values and data lake columns containing up to 1M values.

Problem

• join discovery
• semantic join
• value-level comparison
• high-cardinality columns
• data lakes

Innovation

• semantic join discovery
• value-level join
• sketching
• scalability
• data lake