Farm Your ML-based Query Optimizer's Food! - Human-Guided Training Data Generation -
Summary: DataFarm: white-box generator that learns abstract plan patterns (Markov chains) and instantiates realistic operator-level plans tuned to the user's data. Interpretable active learner with a human-in-the-loop GUI executes few plans, forecasts runtimes with uncertainty, and produces high-quality labeled training sets for ML query optimizers. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Robin van de Water (German National Research Center for Information Technology; Technical University of Berlin)
- 2. Francesco Ventura (German National Research Center for Information Technology; Technical University of Berlin)
- 3. Zoi Kaudi (German National Research Center for Information Technology; Technical University of Berlin)
- 4. Jorge-Arnulfo Quiané-Ruiz (German National Research Center for Information Technology; Technical University of Berlin)
- 5. Volker Markl (German National Research Center for Information Technology; Technical University of Berlin)
BibTeX Citation
@inproceedings{water_cidr22,
address = {Amsterdam, Netherlands},
series = {{CIDR} '22},
title = {{Farm Your ML-based Query Optimizer's Food! - Human-Guided Training Data Generation -}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {van de Water, Robin and Ventura, Francesco and Kaudi, Zoi and Quiané-Ruiz, Jorge-Arnulfo and Markl, Volker},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,536 | Database Gyms | 2023 | CIDR | 5.2529727e-05 |
| 11,065 | Learned Cost Models for Query Optimization: From Batch to Streaming Systems | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,351 | RHEEM: Enabling Cross-Platform Data Processing - May The Big Data Be With You! - | 2018 | VLDB | 7.4937347e-05 |
| 6,024 | Expand your Training Limits! Generating Training Data for ML-based Data Management | 2021 | SIGMOD | 6.0031118e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,468 | Towards a Learning Optimizer for Shared Clouds | 2019 | VLDB |
| 2 | 11,083 | Graph Transformers for Query Plan Representation: Potentials and Challenges | 2025 | VLDB |
| 3 | 5,059 | Steering Query Optimizers: A Practical Take on Big Data Workloads | 2021 | SIGMOD |
| 4 | 2,313 | Active Learning for ML Enhanced Database Systems | 2020 | SIGMOD |
| 5 | 11,067 | Machine Learning for Graph Data Management and Query Processing | 2025 | VLDB |
| 6 | 3,051 | Towards a Hands-Free Query Optimizer through Deep Learning | 2019 | CIDR |
| 7 | 6,271 | Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective | 2024 | VLDB |
| 8 | 2,355 | QueryFormer: A Tree Transformer Model for Query Plan Representation | 2022 | VLDB |
| 9 | 11,845 | Query-Driven Learning for Next Generation Predictive Modeling & Analytics | 2019 | SIGMOD |
| 10 | 6,024 | Expand your Training Limits! Generating Training Data for ML-based Data Management | 2021 | SIGMOD |