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: hb3fd006904b73bbf
Venue: VLDB
Year: 2022
Pagerank: 6.8899861e-05
Overall Rank: 3,969 | 73.32%
DOI: 10.14778/3547305.3547310

Incoming Non-self Citations Over Time

Authors

1. Zhihui Yang (Zhejiang Lab)
2. Zuozhi Wang (University of California Irvine)
3. Yicong Huang (University of California Irvine)
4. Yao Lu (Microsoft)
5. Chen Li (University of California Irvine)
6. X. Sean Wang (Fudan University)

BibTeX Citation

@article{yang_vldb22,
        title = {{Optimizing Machine Learning Inference Queries with Correlative Proxy Models}},
        author = {Yang, Zhihui and Wang, Zuozhi and Huang, Yicong and Lu, Yao and Li, Chen and Wang, X. Sean},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {10},
        pages = {2032--2044},
        doi = {10.14778/3547305.3547310},
        url = {https://doi.org/10.14778/3547305.3547310},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 16 of 16 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
3,508	Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures	2023	VLDB	7.2490197e-05
3,778	Optimizing Video Analytics with Declarative Model Relationships	2023	VLDB	7.0259119e-05
5,551	Aero: Adaptive Query Processing of ML Queries	2025	SIGMOD	6.0872198e-05
5,685	SmartLite: A DBMS-based Serving System for DNN Inference in Resource-constrained Environments	2024	VLDB	6.037958e-05
5,911	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB	5.9501384e-05
6,166	Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving	2025	SIGMOD	5.8631131e-05
6,583	Extract-Transform-Load for Video Streams	2023	VLDB	5.7438181e-05
8,230	Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents	2025	SIGMOD	5.372368e-05
10,044	Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models	2022	VLDB	5.0921006e-05
10,446	Eliminating Redundant Feature Tests in Decision Tree and Random Forest Inference on SQL Predicates	2026	SIGMOD	4.9793485e-05
10,498	ScaleDoc: Scaling LLM-based Predicates over Large Document Collections	2026	SIGMOD	4.9793485e-05
10,858	Sema: A High-performance System for LLM-based Semantic Query Processing	2026	VLDB	4.9793485e-05
11,456	IcedTea: Efficient and Responsive Time-Travel Debugging in Dataflow Systems	2025	VLDB	4.9793485e-05
11,548	Pasta: A Cost-Based Optimizer for Generating Pipelining Schedules for Dataflow DAGs	2024	SIGMOD	4.9793485e-05
11,596	Optimizing Video Queries with Declarative Clues	2024	VLDB	4.9793485e-05
11,728	Udon: Efficient Debugging of User-Defined Functions in Big Data Systems with Line-by-Line Control	2023	SIGMOD	4.9793485e-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.

Rank	Cited Paper	Year	Venue	Pagerank
125	Predicate Migration: Optimizing Queries with Expensive Predicates	1993	SIGMOD	0.00030470848
160	CORDS: Automatic Discovery of Correlations and Soft Functional Dependencies	2004	SIGMOD	0.00027837289
281	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD	0.00022295232
318	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021167555
541	BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics	2020	VLDB	0.00016657685
827	Adaptive Ordering of Pipelined Stream Filters	2004	SIGMOD	0.00013632674
1,082	Approximate Query Processing: No Silver Bullet	2017	SIGMOD	0.00012122749
2,264	An Intermediate Representation for Optimizing Machine Learning Pipelines	2019	VLDB	8.7289107e-05
2,391	DeepLens: Towards a Visual Data Management System	2019	CIDR	8.5365368e-05
2,776	Approximate Selection with Guarantees using Proxies	2020	VLDB	8.0309448e-05
4,182	Rafiki: Machine Learning as an Analytics Service System	2019	VLDB	6.755131e-05
6,143	Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse	2018	VLDB	5.8721471e-05
9,123	Optimization of Multi-Version Expensive Predicates	2007	SIGMOD	5.2254194e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	12,145	Query-Driven Learning for Next Generation Predictive Modeling & Analytics	2019	SIGMOD
2	2,662	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD
3	3,988	Exploiting Correlations for Expensive Predicate Evaluation	2015	SIGMOD
4	7,316	Interactive Demonstration of Probabilistic Predicates	2018	SIGMOD
5	3,874	Accelerating Approximate Aggregation Queries with Expensive Predicates	2021	VLDB
6	3,090	Correlation Sketches for Approximate Join-Correlation Queries	2021	SIGMOD
7	11,931	Accelerating Queries over Unstructured Data with ML	2021	CIDR
8	5,911	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB
9	281	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD
10	10,044	Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models	2022	VLDB