InferDB: In-Database Machine Learning Inference Using Indexes
Summary: Uses a discretizing embedding of selected features and an index mapping embedding cells to aggregated model outputs to approximate end-to-end ML inference inside the DB. Replaces preprocessing and model execution with a transform+lookup, cutting latency by orders of magnitude while retaining similar accuracy. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Ricardo Salazar-Díaz (Hasso Plattner Institute; University of Potsdam)
- 2. Boris Glavic (University of Illinois Chicago)
- 3. Tilmann Rabl (Hasso Plattner Institute; University of Potsdam)
BibTeX Citation
@article{salazardiaz_vldb24,
title = {{InferDB: In-Database Machine Learning Inference Using Indexes}},
author = {Salazar-Díaz, Ricardo and Glavic, Boris and Rabl, Tilmann},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {8},
pages = {1830--1842},
doi = {10.14778/3659437.3659441},
url = {https://doi.org/10.14778/3659437.3659441},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 416 | SystemML: Declarative Machine Learning on Spark | 2016 | VLDB | 0.00018650998 |
| 503 | Towards a Unified Architecture for in-RDBMS Analytics | 2012 | SIGMOD | 0.00017195428 |
| 1,006 | Integrating Association Rule Mining with Relational Database Systems: Alternatives and Implications | 1998 | SIGMOD | 0.00012567476 |
| 2,266 | An Intermediate Representation for Optimizing Machine Learning Pipelines | 2019 | VLDB | 8.7248802e-05 |
| 2,661 | End-to-end Optimization of Machine Learning Prediction Queries | 2022 | SIGMOD | 8.1568473e-05 |
| 4,097 | Distributed Deep Learning on Data Systems: A Comparative Analysis of Approaches | 2021 | VLDB | 6.8064316e-05 |
| 4,852 | Neighbor-Sensitive Hashing | 2016 | VLDB | 6.3776281e-05 |
| 5,778 | The Tensor Data Platform: Towards an AI-centric Database System | 2023 | CIDR | 5.9953658e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,167 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 2 | 2,184 | Extending Relational Query Processing with ML Inference | 2020 | CIDR |
| 3 | 10,459 | EncoderForge: Generating Efficient SQL for Encoders in Machine Learning Inference Pipelines | 2026 | SIGMOD |
| 4 | 5,905 | On Efficient Approximate Queries over Machine Learning Models | 2023 | VLDB |
| 5 | 11,017 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 6 | 3,621 | Learned Index: A Comprehensive Experimental Evaluation | 2023 | VLDB |
| 7 | 282 | Accelerating Machine Learning Inference with Probabilistic Predicates | 2018 | SIGMOD |
| 8 | 4,143 | Hybrid In-Database Inference for Declarative Information Extraction | 2011 | SIGMOD |
| 9 | 6,747 | Mitigating the Impedance Mismatch between Prediction Query Execution and Database Engine | 2025 | SIGMOD |
| 10 | 4,713 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |