DBScholar

Back to papers

InferF: Declarative Factorization of AI/ML Inferences over Joins

Summary: Declarative factorized inference over multi-way joins: push partial ML subcomputations to join-tree nodes to cut redundant inference and join cost. InferF formalizes plan selection for arbitrary analyzable inference expressions and uses greedy/genetic search; up to 11.3x speedup on Velox. (summarized by gpt-5-mini on Apr 11 2026)

Paper ID
ha16a2914e02c2c48
Venue
SIGMOD
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,653 | 28.38%
DOI
10.1145/3786662

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@inproceedings{chowdhury_sigmod26,
        title = {{InferF: Declarative Factorization of AI/ML Inferences over Joins}},
        author = {Chowdhury, Kanchan and Zhou, Lixi and Xie, Lulu and Fu, Xinwei and Zou, Jia},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3786662},
        url = {https://dl.acm.org/doi/10.1145/3786662},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 38 of 38 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
15 How Good Are Query Optimizers, Really? 2016 VLDB 0.00061066921
379 Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources 2018 SIGMOD 0.00019514689
415 SystemML: Declarative Machine Learning on Spark 2016 VLDB 0.0001865959
479 The Making of TPC-DS 2006 VLDB 0.00017622471
521 Learning Linear Regression Models over Factorized Joins 2016 SIGMOD 0.00016929744
680 Amazon Redshift Re-invented 2022 SIGMOD 0.00014828697
730 Learning Generalized Linear Models Over Normalized Data 2015 SIGMOD 0.00014406936
777 To Join or Not to Join? Thinking Twice about Joins before Feature Selection 2016 SIGMOD 0.00014054709
1,256 Towards Linear Algebra over Normalized Data 2017 VLDB 0.00011314687
1,424 Velox: Meta's Unified Execution Engine 2022 VLDB 0.00010719232
1,668 SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle 2020 CIDR 9.9371612e-05
2,199 Enabling and Optimizing Non-linear Feature Interactions in Factorized Linear Algebra 2019 SIGMOD 8.8750296e-05
2,249 Evaluating End-to-End Optimization for Data Analytics Applications in Weld 2018 VLDB 8.7549752e-05
2,264 An Intermediate Representation for Optimizing Machine Learning Pipelines 2019 VLDB 8.7289107e-05
2,299 On Functional Aggregate Queries with Additive Inequalities 2019 PODS 8.6727773e-05
2,400 Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning 2019 VLDB 8.5213814e-05
2,586 Brainwash: A Data System for Feature Engineering 2013 CIDR 8.2560072e-05
2,662 End-to-end Optimization of Machine Learning Prediction Queries 2022 SIGMOD 8.1596229e-05
2,663 A Layered Aggregate Engine for Analytics Workloads 2019 SIGMOD 8.1581558e-05
3,373 F: Regression Models over Factorized Views 2016 VLDB 7.3661025e-05
3,518 A Comparative Evaluation of Systems for Scalable Linear Algebra-based Analytics 2018 VLDB 7.2400627e-05
3,592 Looking Ahead Makes Query Plans Robust: Making the Initial Case with In-Memory Star Schema Data Warehouse Workloads 2017 VLDB 7.1835842e-05
3,985 Designing an Open Framework for Query Optimization and Compilation 2022 VLDB 6.8730085e-05
4,278 QuickFOIL: Scalable Inductive Logic Programming 2015 VLDB 6.6905317e-05
5,289 Tensor Relational Algebra for Distributed Machine Learning System Design 2021 VLDB 6.1940481e-05
5,685 SmartLite: A DBMS-based Serving System for DNN Inference in Resource-constrained Environments 2024 VLDB 6.037958e-05
6,116 ConnectorX: Accelerating Data Loading From Databases to Dataframes 2022 VLDB 5.8815309e-05
6,296 Declarative Sub-Operators for Universal Data Processing 2023 VLDB 5.8195258e-05
6,550 JoinBoost: Grow Trees Over Normalized Data Using Only SQL 2023 VLDB 5.7503043e-05
6,742 Mitigating the Impedance Mismatch between Prediction Query Execution and Database Engine 2025 SIGMOD 5.6910432e-05
6,844 Serving Deep Learning Models with Deduplication from Relational Databases 2022 VLDB 5.6664512e-05
7,386 Lachesis: Automatic Partitioning for UDF-Centric Analytics 2021 VLDB 5.538189e-05
8,165 Pangea: Monolithic Distributed Storage for Data Analytics 2019 VLDB 5.3851885e-05
8,389 PARQO: Penalty-Aware Robust Plan Selection in Query Optimization 2024 VLDB 5.3413016e-05
9,071 Privacy and Accuracy-Aware AI/ML Model Deduplication 2025 SIGMOD 5.2283159e-05
9,179 FEBench: A Benchmark for Real-Time Relational Data Feature Extraction 2023 VLDB 5.2121898e-05
9,748 PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development 2018 SIGMOD 5.1349531e-05
10,235 Scalable and Usable Relational Learning With Automatic Language Bias 2021 SIGMOD 5.0547931e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 5,272 InferDB: In-Database Machine Learning Inference Using Indexes 2024 VLDB
2 8,798 Towards A Polyglot Framework for Factorized ML 2021 VLDB
3 521 Learning Linear Regression Models over Factorized Joins 2016 SIGMOD
4 730 Learning Generalized Linear Models Over Normalized Data 2015 SIGMOD
5 281 Accelerating Machine Learning Inference with Probabilistic Predicates 2018 SIGMOD
6 10,448 EncoderForge: Generating Efficient SQL for Encoders in Machine Learning Inference Pipelines 2026 SIGMOD
7 2,199 Enabling and Optimizing Non-linear Feature Interactions in Factorized Linear Algebra 2019 SIGMOD
8 10,452 Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over Relations 2026 SIGMOD
9 2,846 FactorJoin: A New Cardinality Estimation Framework for Join Queries 2023 SIGMOD
10 10,842 The Data World Is Not Flat: Efficient Factorized Execution for Relational Systems 2026 VLDB