ReStore - Neural Data Completion for Relational Databases

Summary: ReStore uses neural, schema-structured completion for relational tables with missing tuples to synthesize plausible substitutes. It reduces aggregate-query error by up to 390% vs incomplete data alone, enabling automated OLAP without manual imputation. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h6d4e4350db6d1ecb
Venue: SIGMOD
Year: 2021
Pagerank: 5.4741304e-05
Overall Rank: 7,704 | 48.21%
DOI: 10.1145/3448016.3457264

Incoming Non-self Citations Over Time

Authors

1. Benjamin Hilprecht (Technical University of Darmstadt)
2. Carsten Binnig (Technical University of Darmstadt)

BibTeX Citation

@inproceedings{hilprecht_sigmod21,
        title = {{ReStore - Neural Data Completion for Relational Databases}},
        author = {Hilprecht, Benjamin and Binnig, Carsten},
        series = {{SIGMOD} '21},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3448016.3457264},
        url = {https://dl.acm.org/doi/10.1145/3448016.3457264},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,680	Controllable Tabular Data Synthesis Using Diffusion Models	2024	SIGMOD	5.7104433e-05
10,181	In-Database Data Imputation	2024	SIGMOD	5.0653015e-05
11,590	Enriching Relations with Additional Attributes for ER	2024	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 19 of 19 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
104	HoloClean: Holistic Data Repairs with Probabilistic Inference	2017	VLDB	0.00033690989
318	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021167555
406	Deep Unsupervised Cardinality Estimation	2020	VLDB	0.00019045544
547	ERACER: A Database Approach for Statistical Inference and Data Cleaning	2010	SIGMOD	0.00016578131
841	BayesStore: Managing Large, Uncertain Data Repositories with Probabilistic Graphical Models	2008	VLDB	0.00013541445
970	On the Representation and Querying of Sets of Possible Worlds	1987	SIGMOD	0.00012772086
1,043	Data Cleaning: Overview and Emerging Challenges	2016	SIGMOD	0.00012335114
1,082	Approximate Query Processing: No Silver Bullet	2017	SIGMOD	0.00012122749
1,720	A Sample-and-Clean Framework for Fast and Accurate Query Processing on Dirty Data	2014	SIGMOD	9.7965659e-05
2,156	Obtaining Complete Answers from Incomplete Databases	1996	VLDB	8.9455055e-05
2,190	Data Integration: After the Teenage Years	2017	PODS	8.8867887e-05
2,717	Partial Results in Database Systems	2014	SIGMOD	8.0980367e-05
4,171	Data Integration and Machine Learning: A Natural Synergy	2018	SIGMOD	6.7608137e-05
4,253	Sample Debiasing in the Themis Open World Database System	2020	SIGMOD	6.7015395e-05
4,329	Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration	2020	VLDB	6.6597797e-05
4,765	Probabilistic Databases with MarkoViews	2012	VLDB	6.4275411e-05
4,868	Uncertainty Annotated Databases - A Lightweight Approach for Approximating Certain Answers	2019	SIGMOD	6.3748367e-05
6,880	Estimating the Impact of Unknown Unknowns on Aggregate Query Results	2016	SIGMOD	5.6573214e-05
7,427	Local Structure and Determinism in Probabilistic Databases	2012	SIGMOD	5.5304729e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	13,746	Using Deep Learning Models to Replace Large Materialized Views in Relational Database	2021	CIDR
2	11,683	Querying Incomplete Numerical Data: Between Certain and Possible Answers	2023	PODS
3	8,679	Relational Deep Dive: Error-Aware Queries Over Unstructured Data	2026	VLDB
4	861	SnipSuggest: Context-Aware Autocompletion for SQL	2011	VLDB
5	1,714	Spreadsheets in RDBMS for OLAP	2003	SIGMOD
6	4,707	PreQR: Pre-training Representation for SQL Understanding	2022	SIGMOD
7	11,239	Holistic query Approximation via RL Modeling	2025	VLDB
8	5,739	Capturing Missing Tuples and Missing Values	2010	PODS
9	10,853	Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models	2026	VLDB
10	6,146	Identifying the Extent of Completeness of Query Answers over Partially Complete Databases	2015	SIGMOD