Serving Deep Learning Model in Relational Databases

TL;DR

This paper explores architectures for serving deep learning models within relational databases, analyzing their strengths, limitations, and integration challenges to enable efficient data-intensive DL inference.

Contribution

It provides a comprehensive analysis of DL-centric, UDF-centric, and relation-centric architectures, proposing strategies for their integration within RDBMS.

Findings

Identifies key gaps hindering architecture integration

Proposes pathways for seamless architecture combination

Lays groundwork for a new RDBMS supporting DL inference

Abstract

Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently. In this visionary paper, we embark on a comprehensive exploration of representative architectures to address the requirement. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS). The potential relation-centric architecture aims to represent a large-scale tensor computation through relational operators. While each of these architectures demonstrates promise in specific use scenarios, we identify urgent requirements for seamless integration of these architectures and the middle ground in-between these architectures. We delve into the gaps that impede the integration and explore innovative strategies to close them. We present a pathway to establish a novel RDBMS for enabling a broad class of data-intensive DL inference applications.