Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation

Summary: Leva constructs a relational embedding by graphifying the database and learning vectors that summarize the entire data. Downstream supervision filters noisy graph signals, reducing cross-relational feature engineering and data-discovery burden, and boosting ML performance on classification/regression tasks. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h10d3887a42000f77
Venue: SIGMOD
Year: 2022
Pagerank: 7.1540505e-05
Overall Rank: 3,617 | 75.70%
DOI: 10.1145/3514221.3517891

Incoming Non-self Citations Over Time

Authors

1. Zixuan Zhao (University of Chicago)
2. Raul Castro Fernandez (University of Chicago)

BibTeX Citation

@inproceedings{zhao_sigmod22,
        title = {{Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation}},
        author = {Zhao, Zixuan and Fernandez, Raul Castro},
        series = {{SIGMOD} '22},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3514221.3517891},
        url = {https://dl.acm.org/doi/10.1145/3514221.3517891},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,854	Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning	2023	VLDB	9.4961138e-05
3,236	How Large Language Models Will Disrupt Data Management	2023	VLDB	7.4996147e-05
3,924	Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System	2025	SIGMOD	6.9195146e-05
4,525	DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data	2023	SIGMOD	6.559044e-05
6,979	Solo: Data Discovery Using Natural Language Questions Via A Self-Supervised Approach	2023	SIGMOD	5.6272426e-05
8,582	OmniMatch: Joinability Discovery in Data Products	2025	VLDB	5.3097022e-05
8,997	Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation	2023	SIGMOD	5.2400249e-05
10,808	NeurIDA: Dynamic Modeling for Effective In-Database Analytics	2026	VLDB	4.9769913e-05
10,903	MosaicJoin: Compact Semantic Sketches for Value-Level Join Discovery	2026	VLDB	4.9769913e-05
11,010	ARGO: An Interactive Data Governance System for Machine Learning via Hierarchical Reinforcement Learning	2026	VLDB	4.9769913e-05
11,535	Unstructured Data Fusion for Schema and Data Extraction	2024	SIGMOD	4.9769913e-05
11,596	Enriching Relations with Additional Attributes for ER	2024	VLDB	4.9769913e-05

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
377	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019564011
457	Distributed Representations of Tuples for Entity Resolution	2018	VLDB	0.00017899824
779	To Join or Not to Join? Thinking Twice about Joins before Feature Selection	2016	SIGMOD	0.00014048128
1,038	ARDA: Automatic Relational Data Augmentation for Machine Learning	2020	VLDB	0.000123653
1,319	LSH Ensemble: Internet-Scale Domain Search	2016	VLDB	0.00011042864
1,336	Auctus: A Dataset Search Engine for Data Discovery and Augmentation	2021	VLDB	0.00010984121
1,391	Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks	2020	SIGMOD	0.00010812249
3,092	Correlation Sketches for Approximate Join-Correlation Queries	2021	SIGMOD	7.6548729e-05
3,673	Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers?	2018	VLDB	7.1075403e-05
7,880	Learning Over Dirty Data Without Cleaning	2020	SIGMOD	5.4330096e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,808	NeurIDA: Dynamic Modeling for Effective In-Database Analytics	2026	VLDB
2	2,661	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD
3	9,222	Powering In-Database Dynamic Model Slicing for Structured Data Analytics	2024	VLDB
4	8,236	Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents	2025	SIGMOD
5	1,257	Towards Linear Algebra over Normalized Data	2017	VLDB
6	10,241	Scalable and Usable Relational Learning With Automatic Language Bias	2021	SIGMOD
7	11,191	Data Enhancement for Binary Classification of Relational Data	2025	SIGMOD
8	10,158	Structure-Aware Machine Learning over Multi-Relational Databases	2021	SIGMOD
9	1,038	ARDA: Automatic Relational Data Augmentation for Machine Learning	2020	VLDB
10	1,391	Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks	2020	SIGMOD