ApproxML: Efficient Approximate Ad-Hoc ML Models Through Materialization and Reuse
Summary: ApproxML presents materialization-driven approximate ML, reusing previously built models to construct new ones for ad-hoc predictive queries. By caching and composing GLMs, K-means and GMMs, it speeds exploration with bounded accuracy loss, suited to data-management workloads. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Sona Hasani (University of Texas)
- 2. Faezeh Ghaderi (University of Texas)
- 3. Shohedul Hasan (University of Texas)
- 4. Saravanan Thirumuruganathan (Hamad Bin Khalifa University; Qatar Computing Research Institute)
- 5. Abolfazl Asudeh (University of Illinois Chicago)
- 6. Nick Koudas (University of Toronto)
- 7. Gautam Das (University of Texas)
BibTeX Citation
@article{hasani_vldb19,
title = {{ApproxML: Efficient Approximate Ad-Hoc ML Models Through Materialization and Reuse}},
author = {Hasani, Sona and Ghaderi, Faezeh and Hasan, Shohedul and Thirumuruganathan, Saravanan and Asudeh, Abolfazl and Koudas, Nick and Das, Gautam},
journal = {PVLDB},
series = {{VLDB} '19},
volume = {12},
number = {12},
pages = {1906--1909},
doi = {10.14778/3352063.3352096},
url = {https://doi.org/10.14778/3352063.3352096},
year = {2019}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,309 | Materialization and Reuse Optimizations for Production Data Science Pipelines | 2022 | SIGMOD | 5.9189554e-05 |
| 10,751 | Approximating Opaque Top-k Queries | 2025 | SIGMOD | 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 |
|---|---|---|---|---|
| 764 | To Join or Not to Join? Thinking Twice about Joins before Feature Selection | 2016 | SIGMOD | 0.00014226652 |
| 6,038 | Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse | 2018 | VLDB | 5.9990929e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 5,785 | BlinkML: Efficient Maximum Likelihood Estimation with Probabilistic Guarantees | 2019 | SIGMOD |
| 2 | 5,901 | A Scalable AutoML Approach Based on Graph Neural Networks | 2022 | VLDB |
| 3 | 4,798 | Accelerating Generalized Linear Models with MLWeaving: A One-Size-Fits-All System for Any-Precision Learning | 2019 | VLDB |
| 4 | 6,309 | Materialization and Reuse Optimizations for Production Data Science Pipelines | 2022 | SIGMOD |
| 5 | 10,831 | Holistic query Approximation via RL Modeling | 2025 | VLDB |
| 6 | 9,591 | Sapprox: Enabling Efficient and Accurate Approximations on Sub-datasets with Distribution-aware Online Sampling | 2017 | VLDB |
| 7 | 11,169 | Certain and Approximately Certain Models for Statistical Learning | 2024 | SIGMOD |
| 8 | 11,641 | Approximation Algorithms for Large Scale Data Analysis | 2021 | PODS |
| 9 | 9,353 | On Efficient Approximate Queries over Machine Learning Models | 2023 | VLDB |
| 10 | 6,038 | Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse | 2018 | VLDB |