Distributed Numerical and Machine Learning Computations via Two-Phase Execution of Aggregated Join Trees

Summary: Two-phase execution for numerical/ML workloads expressed as aggregated join trees (joins then aggregation). Pilot run collects lineage to enable record-level planning before execution; experiments show this relational two-phase approach as an effective platform for distributed ML. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h6421feb9d6ebb633
Venue: VLDB
Year: 2021
Pagerank: 5.0751093e-05
Overall Rank: 10,064 | 32.54%
DOI: 10.14778/3450980.3450991
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Dimitrije Jankov (Rice University)
2. Binhang Yuan (Rice University)
3. Shangyu Luo (Rice University)
4. Chris Jermaine (Rice University)

BibTeX Citation

@article{jankov_vldb21,
        title = {{Distributed Numerical and Machine Learning Computations via Two-Phase Execution of Aggregated Join Trees}},
        author = {Jankov, Dimitrije and Yuan, Binhang and Luo, Shangyu and Jermaine, Chris},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {7},
        pages = {1228--1240},
        doi = {10.14778/3450980.3450991},
        url = {https://doi.org/10.14778/3450980.3450991},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,474	In-Database Machine Learning with CorgiPile: Stochastic Gradient Descent without Full Data Shuffle	2022	SIGMOD	5.7555547e-05
6,562	JoinBoost: Grow Trees Over Normalized Data Using Only SQL	2023	VLDB	5.7287508e-05
10,770	Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation	2026	VLDB	4.9605343e-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
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0023948467
5	Optimal Aggregation Algorithms for Middleware [Extended Abstract]	2001	PODS	0.0010688884
135	Ripple Joins for Online Aggregation	1999	SIGMOD	0.00029805026
259	An Overview of Query Optimization in Relational Systems	1998	PODS	0.00022881075
340	Trio: A System for Data, Uncertainty, and Lineage	2006	VLDB	0.00020548826
407	Distributed Query Processing In A Relational Data Base System	1978	SIGMOD	0.00019003397
842	Exploiting Inter-Operation Parallelism in XPRS	1992	SIGMOD	0.00013501181
1,722	SMOKE: Fine-grained Lineage at Interactive Speed	2018	VLDB	9.781628e-05
2,002	Track Join: Distributed Joins with Minimal Network Traffic	2014	SIGMOD	9.189062e-05
2,407	Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning	2019	VLDB	8.4928721e-05
2,834	DB4ML – An In-Memory Database Kernel with Machine Learning Support	2020	SIGMOD	7.9442734e-05
2,974	In-Database Learning with Sparse Tensors	2018	PODS	7.7812156e-05
3,520	MLog: Towards Declarative In-Database Machine Learning	2017	VLDB	7.2180592e-05
3,874	Optimizing Nested Queries with Parameter Sort Orders	2005	VLDB	6.9367667e-05
4,088	Dynamically Optimizing Queries over Large Scale Data Platforms	2014	SIGMOD	6.7973616e-05
4,762	Tensor Relational Algebra for Distributed Machine Learning System Design	2021	VLDB	6.4190861e-05
6,733	DistME: A Fast and Elastic Distributed Matrix Computation Engine using GPUs	2019	SIGMOD	5.6788432e-05
9,249	Chasing Similarity: Distribution-aware Aggregation Scheduling	2019	VLDB	5.1860134e-05
9,785	PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development	2018	SIGMOD	5.115551e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	3,072	Design and Evaluation of Parallel Pipelined Join Algorithms	1987	SIGMOD
2	4,912	Parallel Processing of Recursive Queries in Distributed Architectures	1989	VLDB
3	2,407	Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning	2019	VLDB
4	8,291	Accelerate Distributed Joins with Predicate Transfer	2025	SIGMOD
5	5,505	Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra	2021	SIGMOD
6	4,762	Tensor Relational Algebra for Distributed Machine Learning System Design	2021	VLDB
7	1,296	From Theory to Practice: Efficient Join Query Evaluation in a Parallel Database System	2015	SIGMOD
8	12,432	Let's Rethink Join Optimization in Distributed Systems	2015	CIDR
9	9,931	Sharing Aggregate Computation for Distributed Queries	2007	SIGMOD
10	3,638	Advanced Join Strategies for Large-Scale Distributed Computation	2014	VLDB