Back to papers
Optimizing Machine Learning Inference Queries with Correlative Proxy Models
Summary: CORE builds correlated proxy models for ML inference on data, using branch-and-bound search to exploit predicate correlations. It outperforms PP and as-is execution, with up to 63% and 80% throughput gains on text, image, and video datasets.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 12701
- Venue
- VLDB
- Year
- 2022
- Pagerank
- 5.7172262e-05
- Overall Rank
- 5,062 | 64.82%
- DOI
-
10.14778/3547305.3547310
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 13 of 13 citing papers.
| Rank |
Citing Paper |
Year |
Venue |
Pagerank |
| 4,565 |
Optimizing Video Analytics with Declarative Model Relationships |
2023 |
VLDB |
6.0746821e-05 |
| 4,686 |
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures |
2023 |
VLDB |
5.9929067e-05 |
| 6,379 |
SmartLite: A DBMS-based Serving System for DNN Inference in Resource-constrained Environments |
2024 |
VLDB |
5.0844374e-05 |
| 6,868 |
Extract-Transform-Load for Video Streams |
2023 |
VLDB |
4.8982283e-05 |
| 7,334 |
Aero: Adaptive Query Processing of ML Queries |
2025 |
SIGMOD |
4.7538944e-05 |
| 9,311 |
On Efficient Approximate Queries over Machine Learning Models |
2023 |
VLDB |
4.3535588e-05 |
| 9,478 |
Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents |
2025 |
SIGMOD |
4.3300131e-05 |
| 9,677 |
Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving |
2025 |
SIGMOD |
4.3006524e-05 |
| 9,788 |
Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models |
2022 |
VLDB |
4.2799988e-05 |
| 10,887 |
IcedTea: Efficient and Responsive Time-Travel Debugging in Dataflow Systems |
2025 |
VLDB |
4.1905499e-05 |
| 10,999 |
Pasta: A Cost-Based Optimizer for Generating Pipelining Schedules for Dataflow DAGs |
2024 |
SIGMOD |
4.1905499e-05 |
| 11,064 |
Optimizing Video Queries with Declarative Clues |
2024 |
VLDB |
4.1905499e-05 |
| 11,215 |
Udon: Efficient Debugging of User-Defined Functions in Big Data Systems with Line-by-Line Control |
2023 |
SIGMOD |
4.1905499e-05 |
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Semantically Similar Papers