Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload

Summary: Prestroid uses tree-convolution to predict SQL query resource usage from traces, reducing encoding/padding waste in large-scale DL training. On 19k Presto queries over 20PB, it outperforms baselines and cuts memory 13.5x and epoch time 3.45x, with up to 13.2x Azure savings. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6235
Venue: SIGMOD
Year: 2021
Pagerank: 5.910467e-05
Overall Rank: 4,804 | 66.59%
DOI: 10.1145/3448016.3457546

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 16 of 16 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
3,169	QueryFormer: A Tree Transformer Model for Query Plan Representation	2022	VLDB	7.4498425e-05
3,348	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB	7.1904529e-05
3,828	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	6.7208524e-05
5,861	Machine Learning for Databases	2021	VLDB	5.298883e-05
6,328	A Comparative Study and Component Analysis of Query Plan Representation Techniques in ML4DB Studies	2024	VLDB	5.1082882e-05
6,879	Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data	2023	SIGMOD	4.8971368e-05
6,885	PilotScope: Steering Databases with Machine Learning Drivers	2024	VLDB	4.895386e-05
7,753	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD	4.660151e-05
7,828	Modeling Shifting Workloads for Learned Database Systems	2024	SIGMOD	4.6407986e-05
7,854	dbET: Execution Time Distribution-based Plan Selection	2023	SIGMOD	4.6350172e-05
9,485	Spatial Query Optimization With Learning	2024	VLDB	4.3341665e-05
9,852	Machine Unlearning in Learned Databases: An Experimental Analysis	2024	SIGMOD	4.2714575e-05
10,050	APQO: An Adaptive Framework for Parametric Query Optimization	2026	SIGMOD	4.1945683e-05
10,225	LIO: A lightweight and interpretable query optimizer based on an evolutionary forest	2026	VLDB	4.1945683e-05
10,288	TATA: An Efficient Framework for Task Transfer in Query Plan Representation	2026	VLDB	4.1945683e-05
10,849	AXE: A Task Decomposition Approach to Learned LSM Tuning	2025	VLDB	4.1945683e-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
66	Spark SQL: Relational Data Processing in Spark	2015	SIGMOD	0.00061639801
204	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00034784455
333	Neo: A Learned Query Optimizer	2019	VLDB	0.00027206884
806	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00016434274
1,737	QuickSel: Quick Selectivity Learning with Mixture Models	2020	SIGMOD	0.00010720294
2,084	The Case for Predictive Database Systems: Opportunities and Challenges	2011	CIDR	9.5820534e-05
3,658	Towards a Hands-Free Query Optimizer through Deep Learning	2019	CIDR	6.8704209e-05
5,473	Facilitating SQL Query Composition and Analysis	2020	SIGMOD	5.4885366e-05
5,505	A Top-Down Approach to Achieving Performance Predictability in Database Systems	2017	SIGMOD	5.4734224e-05
7,684	AutoToken: Predicting Peak Parallelism for Big Data Analytics at Microsoft	2020	VLDB	4.6796855e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
2,501	DBEst: Revisiting Approximate Query Processing Engines with Machine Learning Models	2019	SIGMOD	8.6453446e-05
5,637	Database Workload Characterization with Query Plan Encoders	2022	VLDB	5.3979505e-05
9,351	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB	4.3524472e-05
329	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD	0.00027249545
11,650	Query-Driven Learning for Next Generation Predictive Modeling & Analytics	2019	SIGMOD	4.1945683e-05
806	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00016434274
884	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.00015654004
9,120	Deep Query Optimization	2019	SIGMOD	4.392741e-05
3,625	Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings	2020	SIGMOD	6.9055212e-05
3,828	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	6.7208524e-05