Serving Deep Learning Models with Deduplication from Relational Databases

Summary: In-database DL model serving with deduplication inside a relational DB, avoiding feature transfer and enabling inference beyond memory. Synergistic storage optimizations—duplication detection, page packing, caching—align tensor blocks with pages, preserve accuracy, and reduce storage, memory, cache misses, and latency; evaluations beat DL frameworks in target scenarios. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 12717
Venue: VLDB
Year: 2022
Pagerank: 4.8463881e-05
Overall Rank: 7,061 | 50.88%
DOI: 10.14778/3547305.3547325

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 7 of 7 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,688	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR	4.4673127e-05
9,408	Experimental Analysis of Large-scale Learnable Vector Storage Compression	2024	VLDB	4.3441378e-05
10,095	NeurStore: Efficient In-database Deep Learning Model Management System	2026	SIGMOD	4.1945683e-05
10,143	Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management	2026	SIGMOD	4.1945683e-05
10,177	InferF: Declarative Factorization of AI/ML Inferences over Joins	2026	SIGMOD	4.1945683e-05
10,325	KEN: An Execution Engine for Unstructured Database Systems	2026	VLDB	4.1945683e-05
10,499	Privacy and Accuracy-Aware AI/ML Model Deduplication	2025	SIGMOD	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 20 of 20 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
67	The Merge/Purge Problem for Large Databases	1995	SIGMOD	0.00061348205
128	An Evaluation of Buffer Management Strategies for Relational Database Systems	1985	VLDB	0.00044535268
280	Eliminating Fuzzy Duplicates in Data Warehouses	2002	VLDB	0.00029113044
557	SystemML: Declarative Machine Learning on Spark	2016	VLDB	0.00020197988
1,234	Ed-Join: An Efficient Algorithm for Similarity Joins With Edit Distance Constraints	2008	VLDB	0.00013122499
2,141	LSH Ensemble: Internet-Scale Domain Search	2016	VLDB	9.4542625e-05
2,152	MISTIQUE: A System to Store and Query Model Intermediates for Model Diagnosis	2018	SIGMOD	9.4239787e-05
2,231	Dedoop: Efficient Deduplication with Hadoop	2012	VLDB	9.2304499e-05
2,804	Extending Relational Query Processing with ML Inference	2020	CIDR	8.0935487e-05
3,528	Distributed Data Deduplication	2016	VLDB	7.0066139e-05
4,701	Tensors: An abstraction for general data processing	2021	VLDB	5.9866564e-05
4,748	Rafiki: Machine Learning as an Analytics Service System	2019	VLDB	5.9526539e-05
4,787	The Relational Data Borg is Learning	2020	VLDB	5.9224501e-05
5,331	Hybrid Storage Management for Database Systems	2013	VLDB	5.5665225e-05
5,487	SPORES: Sum-Product Optimization via Relational Equality Saturation for Large Scale Linear Algebra	2020	VLDB	5.4791501e-05
5,821	Tensor Relational Algebra for Distributed Machine Learning System Design	2021	VLDB	5.3134851e-05
6,644	A Relational Matrix Algebra and its Implementation in a Column Store	2020	SIGMOD	4.9782839e-05
7,476	Lachesis: Automatic Partitioning for UDF-Centric Analytics	2021	VLDB	4.7188928e-05
8,002	Pangea: Monolithic Distributed Storage for Data Analytics	2019	VLDB	4.6088289e-05
9,332	PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development	2018	SIGMOD	4.3556432e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
5,236	Online Deduplication for Databases	2017	SIGMOD	5.611324e-05
3,580	Query Performance Prediction for Concurrent Queries using Graph Embedding	2020	VLDB	6.9500996e-05
2,364	Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries	2020	SIGMOD	8.9554751e-05
884	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.00015654004
13,171	Reimagining Deep Learning Systems Through the Lens of Data Systems	2024	VLDB	-
9,776	Structure-Aware Machine Learning over Multi-Relational Databases	2021	SIGMOD	4.2856106e-05
4,409	Declarative Recursive Computation on an RDBMS	2019	VLDB	6.2104034e-05
3,143	Extracting and Analyzing Hidden Graphs from Relational Databases	2017	SIGMOD	7.4804326e-05
10,499	Privacy and Accuracy-Aware AI/ML Model Deduplication	2025	SIGMOD	4.1945683e-05
13,229	Using Deep Learning Models to Replace Large Materialized Views in Relational Database	2021	CIDR	-