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.
@article{arxiv.2310.04696,
title = {Serving Deep Learning Model in Relational Databases},
author = {Lixi Zhou and Qi Lin and Kanchan Chowdhury and Saif Masood and Alexandre Eichenberger and Hong Min and Alexander Sim and Jie Wang and Yida Wang and Kesheng Wu and Binhang Yuan and Jia Zou},
journal= {arXiv preprint arXiv:2310.04696},
year = {2024}
}
Comments
* Authors are ordered alphabetically; Jia Zou is the corresponding author