RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving

Shuxi Guo, Qi Qi, Haifeng Sun, Jianxin Liao, Jingyu Wang


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%.
Anthology ID:
2025.coling-industry.68
Volume:
Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert, Kareem Darwish, Apoorv Agarwal
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
817–826
Language:
URL:
https://aclanthology.org/2025.coling-industry.68/
DOI:
Bibkey:
Cite (ACL):
Shuxi Guo, Qi Qi, Haifeng Sun, Jianxin Liao, and Jingyu Wang. 2025. RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 817–826, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving (Guo et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-industry.68.pdf