Extending Relational Query Processing with ML Inference

Summary: Raven integrates ML runtimes (e.g., ONNX Runtime) natively into SQL Server and uses a unified IR to enable cross-optimizations between model inference and relational operators. Tight DB/compiler/ML co-optimization yields up to 5.5x native gains and up to 24x with cross-optimizations, enabling enterprise-grade in‑RDBMS scoring. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 360
Venue: CIDR
Year: 2020
Pagerank: 8.0935487e-05
Overall Rank: 2,804 | 80.50%
DOI: -

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 27 of 27 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
2,170	tf.data: A Machine Learning Data Processing Framework	2021	VLDB	9.3821603e-05
2,456	Production Machine Learning Pipelines: Empirical Analysis and Optimization Opportunities	2021	SIGMOD	8.7733773e-05
3,254	Query Processing on Tensor Computation Runtimes	2022	VLDB	7.3161051e-05
3,407	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD	7.1295646e-05
3,875	Cloudy with High Chance of DBMS: A 10-year Prediction for Enterprise-Grade ML	2020	CIDR	6.675257e-05
4,557	Distributed Deep Learning on Data Systems: A Comparative Analysis of Approaches	2021	VLDB	6.087611e-05
4,701	Tensors: An abstraction for general data processing	2021	VLDB	5.9866564e-05
4,948	Designing an Open Framework for Query Optimization and Compilation	2022	VLDB	5.8116879e-05
5,476	Containerized Execution of UDFs: An Experimental Evaluation	2022	VLDB	5.4866534e-05
5,731	Babelfish: Efficient Execution of Polyglot Queries	2022	VLDB	5.3502065e-05
6,327	The Tensor Data Platform: Towards an AI-centric Database System	2023	CIDR	5.1083405e-05
6,378	Mitigating the Impedance Mismatch between Prediction Query Execution and Database Engine	2025	SIGMOD	5.0909804e-05
6,525	Database Technology for the Masses: Sub-Operators as First-Class Entities	2021	VLDB	5.027205e-05
6,541	ConnectorX: Accelerating Data Loading From Databases to Dataframes	2022	VLDB	5.0216945e-05
6,863	Declarative Sub-Operators for Universal Data Processing	2023	VLDB	4.905092e-05
7,061	Serving Deep Learning Models with Deduplication from Relational Databases	2022	VLDB	4.8463881e-05
8,080	Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines	2024	VLDB	4.5911668e-05
8,583	Efficient Execution of User-Defined Functions in SQL Queries	2023	VLDB	4.4919445e-05
8,688	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR	4.4673127e-05
8,716	nsDB: Architecting the Next Generation Database by Integrating Neural and Symbolic Systems	2024	VLDB	4.4618187e-05
8,980	HADAD: A Lightweight Approach for Optimizing Hybrid Complex Analytics Queries	2021	SIGMOD	4.4169807e-05
9,351	On Efficient Approximate Queries over Machine Learning Models	2023	VLDB	4.3524472e-05
9,436	Transforming ML Predictive Pipelines into SQL with MASQ	2021	SIGMOD	4.3430376e-05
9,682	Lindorm TSDB: A Cloud-native Time-series Database for Large-scale Monitoring Systems	2023	VLDB	4.3047774e-05
10,130	MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference	2026	SIGMOD	4.1945683e-05
10,714	Towards Designing Future-Proof Data Processing Systems	2025	VLDB	4.1945683e-05
11,213	Udon: Efficient Debugging of User-Defined Functions in Big Data Systems with Line-by-Line Control	2023	SIGMOD	4.1945683e-05

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
140	The MADlib Analytics Library or MAD Skills, the SQL	2012	VLDB	0.00042270404
365	On the Power of Magic	1987	PODS	0.00025585898
557	SystemML: Declarative Machine Learning on Spark	2016	VLDB	0.00020197988
1,108	Froid: Optimization of Imperative Programs in a Relational Database	2018	VLDB	0.00013984276
2,350	An Intermediate Representation for Optimizing Machine Learning Pipelines	2019	VLDB	8.9788641e-05
3,331	A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference	2020	VLDB	7.2131599e-05
3,875	Cloudy with High Chance of DBMS: A 10-year Prediction for Enterprise-Grade ML	2020	CIDR	6.675257e-05
4,677	Automatically Leveraging MapReduce Frameworks for Data-Intensive Applications	2018	SIGMOD	6.0047822e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
5,337	Learned Index Benefits: Machine Learning Based Index Performance Estimation	2022	VLDB	5.5635208e-05
9,776	Structure-Aware Machine Learning over Multi-Relational Databases	2021	SIGMOD	4.2856106e-05
329	Accelerating Machine Learning Inference with Probabilistic Predicates	2018	SIGMOD	0.00027249545
4,549	Database-Agnostic Workload Management	2019	CIDR	6.0926728e-05
6,775	A Unified Transferable Model for ML-Enhanced DBMS	2022	CIDR	4.9299192e-05
5,473	Facilitating SQL Query Composition and Analysis	2020	SIGMOD	5.4885366e-05
9,993	Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More!	2026	CIDR	4.1945683e-05
6,796	InferDB: In-Database Machine Learning Inference Using Indexes	2024	VLDB	4.9241624e-05
7,338	Aero: Adaptive Query Processing of ML Queries	2025	SIGMOD	4.7584583e-05
3,407	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD	7.1295646e-05