@inproceedings{guo-etal-2025-recstream,
title = "{R}ec{S}tream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving",
author = "Guo, Shuxi and
Qi, Qi and
Sun, Haifeng and
Liao, Jianxin and
Wang, Jingyu",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.68/",
pages = "817--826",
abstract = "Recommendation Models (RMs) are crucial for predicting user preferences and enhancing personalized experiences on large-scale platforms. As the application of recommendation models grows, optimizing their online serving performance has become a significant challenge. However, current serving systems perform poorly under highly concurrent scenarios. To address this, we introduce RecStream, a system designed to optimize stream configurations based on model characteristics for handling high concurrency requests. We employ a hybrid Graph Neural Network architecture to determine the best configurations for various RMs. Experimental results demonstrate that RecStream achieves significant performance improvements, reducing latency by up to 74{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2025-recstream">
<titleInfo>
<title>RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuxi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxin</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recommendation Models (RMs) are crucial for predicting user preferences and enhancing personalized experiences on large-scale platforms. As the application of recommendation models grows, optimizing their online serving performance has become a significant challenge. However, current serving systems perform poorly under highly concurrent scenarios. To address this, we introduce RecStream, a system designed to optimize stream configurations based on model characteristics for handling high concurrency requests. We employ a hybrid Graph Neural Network architecture to determine the best configurations for various RMs. Experimental results demonstrate that RecStream achieves significant performance improvements, reducing latency by up to 74%.</abstract>
<identifier type="citekey">guo-etal-2025-recstream</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.68/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>817</start>
<end>826</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving
%A Guo, Shuxi
%A Qi, Qi
%A Sun, Haifeng
%A Liao, Jianxin
%A Wang, Jingyu
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F guo-etal-2025-recstream
%X Recommendation Models (RMs) are crucial for predicting user preferences and enhancing personalized experiences on large-scale platforms. As the application of recommendation models grows, optimizing their online serving performance has become a significant challenge. However, current serving systems perform poorly under highly concurrent scenarios. To address this, we introduce RecStream, a system designed to optimize stream configurations based on model characteristics for handling high concurrency requests. We employ a hybrid Graph Neural Network architecture to determine the best configurations for various RMs. Experimental results demonstrate that RecStream achieves significant performance improvements, reducing latency by up to 74%.
%U https://aclanthology.org/2025.coling-industry.68/
%P 817-826
Markdown (Informal)
[RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving](https://aclanthology.org/2025.coling-industry.68/) (Guo et al., COLING 2025)
ACL