Selective Late Materialization in Modern Analytical Databases

Summary: Recasts late materialization for vectorized column stores as Selective Late Materialization (SLM), choosing each attribute’s materialization point independently per query. DuckDB integration improves JOB performance 14.7% over early and 8.9% over late materialization, reaching 76.7% per-query latency reduction. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: hbc071169d02c4a24
Venue: VLDB
Year: 2025
Pagerank: 5.0979044e-05
Overall Rank: 9,999 | 32.78%
DOI: 10.14778/3749646.3749717

Incoming Non-self Citations Over Time

Authors

1. Yihao Liu (Tsinghua University)
2. Shaoxuan Tang (Tsinghua University)
3. Yulong Hui (Tsinghua University)
4. Hangrui Zhou (Tsinghua University)
5. Huanchen Zhang (Tsinghua University)

BibTeX Citation

@article{liu_vldb25,
        title = {{Selective Late Materialization in Modern Analytical Databases}},
        author = {Liu, Yihao and Tang, Shaoxuan and Hui, Yulong and Zhou, Hangrui and Zhang, Huanchen},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {11},
        pages = {4616--4628},
        doi = {10.14778/3749646.3749717},
        url = {https://doi.org/10.14778/3749646.3749717},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,830	Bridging the Indexing Gap in Fused GPU Query Engines	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 23 of 23 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
14	MonetDB/X100: Hyper-Pipelining Query Execution	2005	CIDR	0.00064031282
15	How Good Are Query Optimizers, Really?	2016	VLDB	0.00061066921
48	Weaving Relations for Cache Performance	2001	VLDB	0.00043805923
61	Integrating Compression and Execution in Column-Oriented Database Systems	2006	SIGMOD	0.000392237
71	DuckDB: an Embeddable Analytical Database	2019	SIGMOD	0.00037720227
82	Hashing Methods and Relational Algebra Operations	1984	VLDB	0.00036053776
179	The Vertica Analytic Database: C-Store 7 Years Later	2012	VLDB	0.00026611886
215	Morsel-Driven Parallelism: A NUMA-Aware Query Evaluation Framework for the Many-Core Age	2014	SIGMOD	0.00024598661
373	Umbra: A Disk-Based System with In-Memory Performance	2020	CIDR	0.00019711632
634	Performance Tradeoffs in Read-Optimized Databases	2006	VLDB	0.00015373122
680	Amazon Redshift Re-invented	2022	SIGMOD	0.00014828697
906	Data Blocks: Hybrid OLTP and OLAP on Compressed Storage using both Vectorization and Compilation	2016	SIGMOD	0.00013160654
1,424	Velox: Meta's Unified Execution Engine	2022	VLDB	0.00010719232
1,484	Query Processing Techniques for Solid State Drives	2009	SIGMOD	0.00010535051
1,694	Self-organizing Tuple Reconstruction in Column-stores	2009	SIGMOD	9.8562172e-05
2,818	To Partition, or Not to Partition, That is the Join Question in a Real System	2021	SIGMOD	7.9739791e-05
3,001	ClickHouse - Lightning Fast Analytics for Everyone	2024	VLDB	7.7667824e-05
3,432	Cache-Conscious Radix-Decluster Projections	2004	VLDB	7.3040202e-05
3,592	Looking Ahead Makes Query Plans Robust: Making the Initial Case with In-Memory Star Schema Data Warehouse Workloads	2017	VLDB	7.1835842e-05
4,074	Apache Arrow DataFusion: A Fast, Embeddable, Modular Analytic Query Engine	2024	SIGMOD	6.8198673e-05
4,153	LeCo: Lightweight Compression via Learning Serial Correlations	2024	SIGMOD	6.776246e-05
7,321	An Examination of CXL Memory Use Cases for In-Memory Database Management Systems using SAP HANA	2024	VLDB	5.5534395e-05
10,074	Databases in the Era of Memory-Centric Computing	2025	CIDR	5.0855548e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,950	Debunking the Myth of Join Ordering: Toward Robust SQL Analytics	2025	SIGMOD
2	654	Materialization Optimizations for Feature Selection Workloads	2014	SIGMOD
3	5,044	Lightweight Cardinality Estimation in LSM-based Systems	2018	SIGMOD
4	7,078	DuckPGQ: Efficient Property Graph Queries in an analytical RDBMS	2023	CIDR
5	7,774	Adaptive Factorization Using Linear-Chained Hash Tables	2025	CIDR
6	10,768	One Join Order Does Not Fit All: Reducing Intermediate Results with Per-Split Query Plans	2026	VLDB
7	6,392	Selection Pushdown in Column Stores using Bit Manipulation Instructions	2023	SIGMOD
8	9,566	Saving Private Hash Join	2025	VLDB
9	9,816	Supporting Scalable Analytics with Latency Constraints	2015	VLDB
10	10,304	Data Chunk Compaction in Vectorized Execution	2025	SIGMOD