NeuroSketch: Fast and Approximate Evaluation of Range Aggregate Queries with Neural Networks

Summary: Models RAQ answers by learning query behavior, not data, enabling query distribution dependent error bounds. NeuroSketch implements this approach and delivers faster, more accurate RAQ evaluation across real, TPC-benchmark, and synthetic data. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6665
Venue: SIGMOD
Year: 2023
Pagerank: 5.324758e-05
Overall Rank: 9,101 | 37.56%
DOI: 10.1145/3588954

Incoming Non-self Citations Over Time

Authors

1. Sepanta Zeighami (University of Southern California)
2. Cyrus Shahabi (University of Southern California)
3. Vatsal Sharan (University of Southern California)

BibTeX Citation

@inproceedings{zeighami_sigmod23,
        title = {{NeuroSketch: Fast and Approximate Evaluation of Range Aggregate Queries with Neural Networks}},
        author = {Zeighami, Sepanta and Shahabi, Cyrus and Sharan, Vatsal},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3588954},
        url = {https://dl.acm.org/doi/10.1145/3588954},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,704	ASM: Harmonizing Autoregressive Model, Sampling, and Multi-dimensional Statistics Merging for Cardinality Estimation	2024	SIGMOD	5.797374e-05
7,351	PairwiseHist: Fast, Accurate and Space-Efficient Approximate Query Processing with Data Compression	2024	VLDB	5.6354898e-05

Outgoing Citations (Sorted by Pagerank)

Showing 12 of 12 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
9	Online Aggregation	1997	SIGMOD	0.00077458002
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035838391
323	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021264788
401	Deep Unsupervised Cardinality Estimation	2020	VLDB	0.00019092557
476	The Making of TPC-DS	2006	VLDB	0.00017860667
513	NeuroCard: One Cardinality Estimator for All Tables	2021	VLDB	0.00017190574
772	VerdictDB: Universalizing Approximate Query Processing	2018	SIGMOD	0.00014147905
1,799	DBEst: Revisiting Approximate Query Processing Engines with Machine Learning Models	2019	SIGMOD	9.7326398e-05
3,086	A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation	2021	SIGMOD	7.7708642e-05
6,804	A Neural Database for Differentially Private Spatial Range Queries	2022	VLDB	5.768025e-05
7,206	Selectivity Functions of Range Queries are Learnable*	2022	SIGMOD	5.6731116e-05
7,668	A Neural Approach to Spatio-Temporal Data Release with User-Level Differential Privacy	2023	SIGMOD	5.5711643e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,845	Query-Driven Learning for Next Generation Predictive Modeling & Analytics	2019	SIGMOD
2	9,601	Low Rank Learning for Offline Query Optimization	2025	SIGMOD
3	10,831	Holistic query Approximation via RL Modeling	2025	VLDB
4	4,789	Learned Approximate Query Processing: Make it Light, Accurate and Fast	2021	CIDR
5	563	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB
6	5,132	Facilitating SQL Query Composition and Analysis	2020	SIGMOD
7	10,290	Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA	2026	SIGMOD
8	697	Selectivity Estimation for Range Predicates using Lightweight Models	2019	VLDB
9	2,175	From Natural Language Processing to Neural Databases	2021	VLDB
10	9,353	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB