Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data

Summary: DDUp is an updatability framework for learned DB components facing insertion-driven shifts, pairing OOD detection with efficient updates. It uses a test to flag OOD data and a distillation-based update to keep AQP, CE, DG accurate without retraining. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h25cfda59f2c4ca76
Venue: SIGMOD
Year: 2023
Pagerank: 5.9979958e-05
Overall Rank: 5,728 | 61.61%
DOI: 10.1145/3588713

Incoming Non-self Citations Over Time

Authors

1. Meghdad Kurmanji (University of Warwick)
2. Peter Triantafillou (University of Warwick)

BibTeX Citation

@inproceedings{kurmanji_sigmod23,
        title = {{Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data}},
        author = {Kurmanji, Meghdad and Triantafillou, Peter},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3588713},
        url = {https://dl.acm.org/doi/10.1145/3588713},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 12 of 12 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
5,453	Eraser: Eliminating Performance Regression on Learned Query Optimizer	2024	VLDB	6.1077838e-05
5,854	Modeling Shifting Workloads for Learned Database Systems	2024	SIGMOD	5.9520525e-05
7,092	E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model	2025	VLDB	5.5868637e-05
8,050	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR	5.3839177e-05
8,825	PACE: Poisoning Attacks on Learned Cardinality Estimation	2024	SIGMOD	5.2543246e-05
8,975	Machine Unlearning in Learned Databases: An Experimental Analysis	2024	SIGMOD	5.2343759e-05
9,814	Understanding Robustness Issues of Updatable Learned Indexes: [Experiments & Analysis]	2026	SIGMOD	5.1121061e-05
10,561	NeurBench: A Benchmark Suite for Learned Database Components with Drift Modeling: [Experiments & Analysis]	2026	SIGMOD	4.9605343e-05
10,608	Rainbow: Risk-aware Index Benefit Estimation Facing Out Of Distribution Workloads	2026	SIGMOD	4.9605343e-05
10,869	NeurIDA: Dynamic Modeling for Effective In-Database Analytics	2026	VLDB	4.9605343e-05
10,873	BaCon: Efficient Batch Processing of Counting Queries	2026	VLDB	4.9605343e-05
10,994	TATA: An Efficient Framework for Task Transfer in Query Plan Representation	2026	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 27 of 27 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
74	Automatic Database Management System Tuning Through Large-scale Machine Learning	2017	SIGMOD	0.00037164008
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035920657
142	Neo: A Learned Query Optimizer	2019	VLDB	0.00029114937
309	An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning	2019	SIGMOD	0.0002143249
320	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021128745
355	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00020146245
405	Deep Unsupervised Cardinality Estimation	2020	VLDB	0.00019020138
411	QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning	2019	VLDB	0.0001874043
427	ALEX: An Updatable Adaptive Learned Index	2020	SIGMOD	0.00018429918
508	NeuroCard: One Cardinality Estimator for All Tables	2021	VLDB	0.00017108973
793	Random Sampling over Joins Revisited	2018	SIGMOD	0.00013903938
870	Learning Multi-dimensional Indexes	2020	SIGMOD	0.0001332034
1,064	Are We Ready For Learned Cardinality Estimation?	2021	VLDB	0.00012181459
1,190	Tsunami: A Learned Multi-dimensional Index for Correlated Data and Skewed Workloads	2021	VLDB	0.00011564169
1,583	Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries	2020	SIGMOD	0.00010148362
1,839	DBEst: Revisiting Approximate Query Processing Engines with Machine Learning Models	2019	SIGMOD	9.5187688e-05
2,009	FLAT: Fast, Lightweight and Accurate Method for Cardinality Estimation	2021	VLDB	9.1813272e-05
2,180	Data Synthesis based on Generative Adversarial Networks	2018	VLDB	8.9007609e-05
2,290	Active Learning for ML Enhanced Database Systems	2020	SIGMOD	8.6813363e-05
2,828	Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings	2020	SIGMOD	7.9476509e-05
3,689	Detecting Change in Data Streams	2004	VLDB	7.078365e-05
3,967	Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload	2021	SIGMOD	6.8772718e-05
4,549	One Model to Rule them All: Towards Zero-Shot Learning for Databases	2022	CIDR	6.5328866e-05
4,792	Learned Approximate Query Processing: Make it Light, Accurate and Fast	2021	CIDR	6.4010108e-05
5,671	PGMJoins: Random Join Sampling with Graphical Models	2021	SIGMOD	6.026372e-05
6,402	A Unified Transferable Model for ML-Enhanced DBMS	2022	CIDR	5.7800842e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,490	Are Learned DBMS Components Robust to Workload Drift?: [Experiments & Analysis]	2026	SIGMOD
2	3,269	Robust Query Driven Cardinality Estimation under Changing Workloads	2023	VLDB
3	1,583	Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries	2020	SIGMOD
4	7,446	Learning to be a Statistician: Learned Estimator for Number of Distinct Values	2022	VLDB
5	5,854	Modeling Shifting Workloads for Learned Database Systems	2024	SIGMOD
6	1,064	Are We Ready For Learned Cardinality Estimation?	2021	VLDB
7	4,792	Learned Approximate Query Processing: Make it Light, Accurate and Fast	2021	CIDR
8	4,479	Lightweight and Accurate Cardinality Estimation by Neural Network Gaussian Process	2022	SIGMOD
9	320	DeepDB: Learn from Data, not from Queries!	2020	VLDB
10	8,975	Machine Unlearning in Learned Databases: An Experimental Analysis	2024	SIGMOD