Alignment-Guided Largest Table Overlap Size Estimation

2026-07-03

AI Summary

Accurately and efficiently estimating the maximum table overlap ratio in heterogeneous tabular corpora faces three key challenges: neglecting row-column structural constraints, lacking explicit alignment signals, and overfitting to value distributions of specific corpora, which undermines cross-domain generalization. To address these issues, this work proposes ALORE, the first method that jointly leverages dual-view row-column hypergraph encoding and an alignment-guided training objective to model structural constraints and inject alignment signals without performing explicit alignment operations. Additionally, ALORE introduces a domain-robust value embedding strategy to enhance generalization. Experiments demonstrate that ALORE reduces MAE by up to 55% across multiple cross-domain datasets and by 69% under zero-shot transfer settings, while achieving up to an 89× speedup in inference and significantly improving query-by-table retrieval performance.

Abstract

Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table retrieval in large table repositories. The first and the state-of-the-art estimator Armadillo improves efficiency by embedding each table independently and approximating overlap ratio via embedding similarity. However, accurate estimation in heterogeneous repositories remains limited by three challenges: (C1) overlap depends on row-column structure, i.e., each matched cell must preserve both its row and column membership under a joint alignment of the two tables, but existing encodings leave this structure to be inferred indirectly; (C2) independent encoding provides no explicit channel for inter-table alignment signals, biasing prediction toward global similarity; (C3) naive value encodings overfit to corpus-specific distributions, causing cross-domain degradation. Hence, we propose ALORE, a scalable and domain-robust overlap ratio estimator built on three principles: (P1) explicitly represent row-column structure; (P2) expose inter-table alignment signals during training without expensive alignment search; (P3) reduce sensitivity to corpus-specific value distributions. ALORE instantiates these principles with a Two-View Row-Column Hypergraph encoder, alignment-guided objectives with inexpensive interaction signals, and a domain-robust value mapping. Experiments on multiple datasets spanning diverse domains and scales, including a large real-world corpus beyond prior benchmarks, show that ALORE outperforms the state of the art. ALORE reduces MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup. We further validate its effectiveness for query-by-table retrieval.

Problem

• table overlap estimation
• query-by-table retrieval
• heterogeneous table repositories
• row-column structure
• domain robustness

Innovation

• table overlap estimation
• row-column structure
• alignment-guided learning
• domain-robust encoding
• hypergraph encoder