Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples

Summary: Auto‑Tables auto-synthesizes multi-step pipelines (e.g., Python) to convert non‑relational “wild” tables into canonical row‑entity / column‑attribute relational form without requiring examples. On a 244-case benchmark it solves >70% at interactive latency, offering zero‑example end‑to‑end table preparation. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: hdb0cc99d82d27615
Venue: VLDB
Year: 2023
Pagerank: 6.429338e-05
Overall Rank: 4,740 | 68.23%
DOI: 10.14778/3611479.3611534
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Peng Li (Georgia Institute of Technology)
2. Yeye He (Microsoft)
3. Cong Yan (Microsoft)
4. Yue Wang (Microsoft)
5. Surajit Chaudhuri (Microsoft)

BibTeX Citation

@article{li_vldb23,
        title = {{Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples}},
        author = {Li, Peng and He, Yeye and Yan, Cong and Wang, Yue and Chaudhuri, Surajit},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {11},
        pages = {3391--3403},
        doi = {10.14778/3611479.3611534},
        url = {https://doi.org/10.14778/3611479.3611534},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,669	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD	9.9157758e-05
7,292	AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework	2025	VLDB	5.5484494e-05
7,548	Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence	2025	VLDB	5.481283e-05
7,802	Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations	2024	SIGMOD	5.4336348e-05
10,405	NOAH: A System for Analyzing Non-relational Tables Using Natural Language	2027	SIGMOD	4.9605343e-05
10,496	BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search	2026	SIGMOD	4.9605343e-05
10,908	EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries	2026	VLDB	4.9605343e-05
10,939	DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation	2026	VLDB	4.9605343e-05
11,679	Utopia: Automatic Pivot Table Assistant	2024	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
366	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019902067
520	Query by Output	2009	SIGMOD	0.00016910379
1,111	Foofah: Transforming Data By Example	2017	SIGMOD	0.00011946262
2,608	Auto-Join: Joining Tables by Leveraging Transformations	2017	VLDB	8.209962e-05
2,645	Auto-Suggest: Learning-to-Recommend Data Preparation Steps Using Data Science Notebooks	2020	SIGMOD	8.1641056e-05
2,746	Transform-Data-by-Example (TDE): An Extensible Search Engine for Data Transformations	2018	VLDB	8.0458815e-05
3,897	Navigating the Data Lake with DATAMARAN: Automatically Extracting Structure from Log Datasets	2018	SIGMOD	6.9202872e-05
4,005	Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search	2021	VLDB	6.8448428e-05
4,444	Auto-Transform: Learning-to-Transform by Patterns	2020	VLDB	6.5812416e-05
5,507	PATSQL: Efficient Synthesis of SQL Queries from Example Tables with Quick Inference of Projected Columns	2021	VLDB	6.0882949e-05
9,008	Auto-BI: Automatically Build BI-Models Leveraging Local Join Prediction and Global Schema Graph	2023	VLDB	5.2245403e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	8,400	Automated Migration of Hierarchical Data to Relational Tables using Programming-by-Example	2018	VLDB
2	11,858	Towards Auto-Generated Data Systems	2023	VLDB
3	3,467	Automatic Discovery of Attributes in Relational Databases	2011	SIGMOD
4	4,287	Automatic Example Queries for Ad Hoc Databases	2011	SIGMOD
5	12,430	Synthesizing Data Programs	2015	CIDR
6	6,037	Tables As a Paradigm for Querying and Restructuring	1996	PODS
7	4,444	Auto-Transform: Learning-to-Transform by Patterns	2020	VLDB
8	7,548	Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence	2025	VLDB
9	4,005	Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search	2021	VLDB
10	2,608	Auto-Join: Joining Tables by Leveraging Transformations	2017	VLDB