@article{liu2023optimizing,
author = {Liu, Rui and Park, Kwanghyun and Psallidas, Fotis and Zhu, Xiaoyong and Mo, Jinghui and Sen, Rathijit and Interlandi, Matteo and Karanasos, Konstantinos and Tian, Yuanyuan and Camacho-Rodríguez, Jesús},
title = {Optimizing Data Pipelines for Machine Learning in Feature Stores},
year = {2023},
month = {August},
abstract = {Data pipelines (i.e., converting raw data to features) are critical for machine learning (ML) models, yet their development and management is time-consuming. Feature stores have recently emerged as a new "DBMS-for-ML" with the premise of enabling data scientists and engineers to define and manage their data pipelines. While current feature stores fulfill their promise from a functionality perspective, they are resource-hungry---with ample opportunities for implementing database-style optimizations to enhance their performance. In this paper, we propose a novel set of optimizations specifically targeted for point-in-time join, which is a critical operation in data pipelines. We implement these optimizations on top of Feathr: a widely-used feature store, and evaluate them on use cases from both the TPCx-AI benchmark and real-world online retail scenarios. Our thorough experimental analysis shows that our optimizations can accelerate data pipelines by up to 3× over state-of-the-art baselines.},
url = {http://approjects.co.za/?big=en-us/research/publication/optimizing-data-pipelines-for-machine-learning-in-feature-stores/},
pages = {4230-4239},
journal = {Proc. VLDB Endow.},
volume = {16},
}