MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery
Summary: MosaicJoin uses compact value-level semantic sketches to approximate column joinability, preserving fine-grained alignment without exhaustive comparisons. Training-free query subsampling provides accuracy guarantees and up to 66× faster retrieval, scaling to million-value columns. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Grace Fan (New York University)
- 2. Eden Wu (New York University)
- 3. Majid Daliri (New York University)
- 4. Juliana Freire (New York University)
BibTeX Citation
@article{fan_vldb26,
title = {{MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery}},
author = {Fan, Grace and Wu, Eden and Daliri, Majid and Freire, Juliana},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3745--3758},
doi = {10.14778/3836663.3836722},
url = {https://doi.org/10.14778/3836663.3836722},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,108 | Semantic Data Systems: From Data Management to Data Understanding | 2026 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 31 of 31 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,947 | DiskJoin: Large-scale Vector Similarity Join with SSD | 2026 | SIGMOD |
| 2 | 9,935 | Approximate Sketches | 2024 | SIGMOD |
| 3 | 202 | Efficient set joins on similarity predicates | 2004 | SIGMOD |
| 4 | 679 | JOSIE: Overlap Set Similarity Search for Finding Joinable Tables in Data Lakes | 2019 | SIGMOD |
| 5 | 1,742 | Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning | 2023 | VLDB |
| 6 | 8,434 | Fast Approximate Similarity Join in Vector Databases | 2025 | SIGMOD |
| 7 | 10,232 | Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees | 2026 | VLDB |
| 8 | 3,093 | Correlation Sketches for Approximate Join-Correlation Queries | 2021 | SIGMOD |
| 9 | 10,745 | Qualitative Join Discovery in Data Lakes using Examples | 2026 | SIGMOD |
| 10 | 2,370 | DeepJoin: Joinable Table Discovery with Pre-trained Language Models | 2023 | VLDB |