Jevnexus speeds up decision based schema matching with less computing
Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching
DatabasesArtificial IntelligenceMachine Learning
Summary
Matching data columns between different databases is tricky because it involves deciding if columns correspond to each other. The authors introduce JevNexus, a system that quickly makes these decisions by combining different sources of information and only slows down to double-check when needed. It works as well as a previous system but runs about seven times faster. This saves a lot of computing time while keeping accuracy high.
What this means in practice
- •For database engineers: Accelerate and improve the accuracy of matching schema columns across databases for data integration tasks by applying JevNexus’s decision-focused approach.
- •For data pipeline developers: Reduce the time required for schema alignment steps in ETL pipelines while maintaining matching quality using JevNexus’s efficient selective refinement mechanism.
Authors
Runze Li, Hanchen Wang, Ying Zhang, Wenjie Zhang
Abstract
Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small. The evaluation covers 561 cases from six benchmark families. JevNexus obtains dataset-macro MRR and Hits@1 of 0.930 and 0.909, compared with 0.926 and 0.903 for Magneto, while reducing mean latency from 123.452 to 15.929 seconds (7.750). Paired analysis finds no statistically significant difference in either MRR or Hits@1. The gate invokes listwise refinement for only 5.665% of source columns and avoids the degradation caused by unconditional refinement. Code and experimental artifacts are available at https://github.com/RazeenLI/JevNexus.