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
7679
Venue
SIGMOD
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,466 | 28.20%
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
18 How Good Are Query Optimizers, Really? 2016 VLDB 0.00059284255
415 SystemML: Declarative Machine Learning on Spark 2016 VLDB 0.0001888524
445 Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources 2018 SIGMOD 0.00018336751
476 The Making of TPC-DS 2006 VLDB 0.00017860667
536 Learning Linear Regression Models over Factorized Joins 2016 SIGMOD 0.0001693369
715 Learning Generalized Linear Models Over Normalized Data 2015 SIGMOD 0.00014655327
764 To Join or Not to Join? Thinking Twice about Joins before Feature Selection 2016 SIGMOD 0.00014226652
818 Amazon Redshift Re-invented 2022 SIGMOD 0.00013822916
1,235 Towards Linear Algebra over Normalized Data 2017 VLDB 0.00011548457
1,756 SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle 2020 CIDR 9.8172465e-05
1,757 Velox: Meta's Unified Execution Engine 2022 VLDB 9.8166984e-05
2,179 Enabling and Optimizing Non-linear Feature Interactions in Factorized Linear Algebra 2019 SIGMOD 9.0146333e-05
2,239 An Intermediate Representation for Optimizing Machine Learning Pipelines 2019 VLDB 8.8875753e-05
2,266 On Functional Aggregate Queries with Additive Inequalities 2019 PODS 8.8391372e-05
2,316 Evaluating End-to-End Optimization for Data Analytics Applications in Weld 2018 VLDB 8.7596739e-05
2,370 Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning 2019 VLDB 8.6795925e-05
2,604 Brainwash: A Data System for Feature Engineering 2013 CIDR 8.3524514e-05
2,769 A Layered Aggregate Engine for Analytics Workloads 2019 SIGMOD 8.1465406e-05
2,865 End-to-end Optimization of Machine Learning Prediction Queries 2022 SIGMOD 8.0180243e-05
3,334 F: Regression Models over Factorized Views 2016 VLDB 7.5110164e-05
3,459 A Comparative Evaluation of Systems for Scalable Linear Algebra-based Analytics 2018 VLDB 7.3953716e-05
3,571 Looking Ahead Makes Query Plans Robust: Making the Initial Case with In-Memory Star Schema Data Warehouse Workloads 2017 VLDB 7.2991953e-05
4,190 QuickFOIL: Scalable Inductive Logic Programming 2015 VLDB 6.8431849e-05
4,215 Designing an Open Framework for Query Optimization and Compilation 2022 VLDB 6.8275676e-05
5,195 Tensor Relational Algebra for Distributed Machine Learning System Design 2021 VLDB 6.3232105e-05
5,706 SmartLite: A DBMS-based Serving System for DNN Inference in Resource-constrained Environments 2024 VLDB 6.1144255e-05
6,253 Declarative Sub-Operators for Universal Data Processing 2023 VLDB 5.940599e-05
6,585 JoinBoost: Grow Trees Over Normalized Data Using Only SQL 2023 VLDB 5.8350362e-05
6,614 Mitigating the Impedance Mismatch between Prediction Query Execution and Database Engine 2025 SIGMOD 5.8216658e-05
6,628 ConnectorX: Accelerating Data Loading From Databases to Dataframes 2022 VLDB 5.8197537e-05
6,708 Serving Deep Learning Models with Deduplication from Relational Databases 2022 VLDB 5.7964983e-05
7,311 Lachesis: Automatic Partitioning for UDF-Centric Analytics 2021 VLDB 5.6491618e-05
8,001 Pangea: Monolithic Distributed Storage for Data Analytics 2019 VLDB 5.508791e-05
8,305 PARQO: Penalty-Aware Robust Plan Selection in Query Optimization 2024 VLDB 5.4568571e-05
8,908 Privacy and Accuracy-Aware AI/ML Model Deduplication 2025 SIGMOD 5.3483178e-05
9,433 FEBench: A Benchmark for Real-Time Relational Data Feature Extraction 2023 VLDB 5.2696166e-05
9,572 PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development 2018 SIGMOD 5.2528121e-05
10,042 Scalable and Usable Relational Learning With Automatic Language Bias 2021 SIGMOD 5.1708123e-05
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 1,235 Towards Linear Algebra over Normalized Data 2017 VLDB
2 5,456 InferDB: In-Database Machine Learning Inference Using Indexes 2024 VLDB
3 8,638 Towards A Polyglot Framework for Factorized ML 2021 VLDB
4 536 Learning Linear Regression Models over Factorized Joins 2016 SIGMOD
5 715 Learning Generalized Linear Models Over Normalized Data 2015 SIGMOD
6 295 Accelerating Machine Learning Inference with Probabilistic Predicates 2018 SIGMOD
7 10,232 EncoderForge: Generating Efficient SQL for Encoders in Machine Learning Inference Pipelines 2026 SIGMOD
8 2,179 Enabling and Optimizing Non-linear Feature Interactions in Factorized Linear Algebra 2019 SIGMOD
9 10,237 Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over Relations 2026 SIGMOD
10 2,991 FactorJoin: A New Cardinality Estimation Framework for Join Queries 2023 SIGMOD