HyperBlocker: Accelerating Rule-based Blocking in Entity Resolution using GPUs

Summary: HyperBlocker accelerates rule-based entity-resolution blocking via pipelined CPU–GPU execution, data/rule-aware planning, and hardware-conscious GPU parallelism. It delivers 6.8–9.1× faster blocking and ≥30% faster end-to-end ER than prior systems at comparable accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: h2e1050778603eab8
Venue: VLDB
Year: 2025
Pagerank: 5.157794e-05
Overall Rank: 9,475 | 36.49%
DOI: 10.14778/3705829.3705847
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Xiaoke Zhu (Beihang University; Shenzhen University)
2. Min Xie (Shenzhen University)
3. Ting Deng (Beihang University)
4. Qi Zhang (Meta)

BibTeX Citation

@article{zhu_vldb25,
        title = {{HyperBlocker: Accelerating Rule-based Blocking in Entity Resolution using GPUs}},
        author = {Zhu, Xiaoke and Xie, Min and Deng, Ting and Zhang, Qi},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {2},
        pages = {308--321},
        doi = {10.14778/3705829.3705847},
        url = {https://doi.org/10.14778/3705829.3705847},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,243	CloudGlide: Deconstructing the Landscape of Cloud-Based Analytics	2025	VLDB	5.1864799e-05
10,856	MGI: A Communication Framework for Data Processing in Massive GPU Infrastructures	2026	VLDB	4.9605343e-05
11,254	Rule-Based Graph Cleaning with GPUs on a Single Machine	2025	SIGMOD	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 22 of 22 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
40	The Case for Learned Index Structures	2018	SIGMOD	0.00046249672
129	Efficient and Extensible Algorithms for Multi Query Optimization	2000	SIGMOD	0.00030314403
132	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.00030213215
142	Neo: A Learned Query Optimizer	2019	VLDB	0.00029114937
158	Deep Learning for Entity Matching: A Design Space Exploration	2018	SIGMOD	0.00028049555
459	Distributed Representations of Tuples for Entity Resolution	2018	VLDB	0.00017863654
1,650	Falcon: Scaling Up Hands-Off Crowdsourced Entity Matching to Build Cloud Services	2017	SIGMOD	9.9690948e-05
1,812	Tuplex: Data Science in Python at Native Code Speed	2021	SIGMOD	9.5747668e-05
2,068	Dedoop: Efficient Deduplication with Hadoop	2012	VLDB	9.0703184e-05
2,124	Opening the Black Boxes in Data Flow Optimization	2012	VLDB	8.9915327e-05
2,438	Cardinality Estimation Using Sample Views with Quality Assurance	2007	SIGMOD	8.4532693e-05
2,520	Deep Learning for Blocking in Entity Matching: A Design Space Exploration	2021	VLDB	8.3343971e-05
2,954	Distributed Data Deduplication	2016	VLDB	7.8045942e-05
3,280	Large-Scale Collective Entity Matching	2011	VLDB	7.4495028e-05
3,745	BLAST: a Loosely Schema-aware Meta-blocking Approach for Entity Resolution	2016	VLDB	7.0370829e-05
3,833	Magellan: Toward Building Entity Matching Management Systems over Data Science Stacks	2016	VLDB	6.9736073e-05
6,400	Selection Pushdown in Column Stores using Bit Manipulation Instructions	2023	SIGMOD	5.7811299e-05
6,539	Parallel Discrepancy Detection and Incremental Detection	2021	VLDB	5.7351897e-05
7,892	Rock: Cleaning Data by Embedding ML in Logic Rules	2024	SIGMOD	5.4156936e-05
8,002	Efficient Execution of User-Defined Functions in SQL Queries	2023	VLDB	5.3927693e-05
9,645	Discovering Top-k Rules using Subjective and Objective Criteria	2023	SIGMOD	5.1332977e-05
10,373	Parallel Rule Discovery from Large Datasets by Sampling	2022	SIGMOD	5.0005386e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,373	Parallel Rule Discovery from Large Datasets by Sampling	2022	SIGMOD
2	4,691	Entity Resolution with Hierarchical Graph Attention Networks	2022	SIGMOD
3	5,070	BEER: Blocking for Effective Entity Resolution	2021	SIGMOD
4	459	Distributed Representations of Tuples for Entity Resolution	2018	VLDB
5	2,520	Deep Learning for Blocking in Entity Matching: A Design Space Exploration	2021	VLDB
6	11,930	Generalized Supervised Meta-blocking	2022	VLDB
7	10,242	Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity Resolution	2024	VLDB
8	5,085	Supervised Meta-blocking	2014	VLDB
9	2,120	Comparative Analysis of Approximate Blocking Techniques for Entity Resolution	2016	VLDB
10	1,309	Entity Resolution with Iterative Blocking	2009	SIGMOD