Scalable High-Performance Architecture for Evolving Recommender System
Pages 154 - 162
Abstract
Recommender systems are expected to scale to the requirement of the large number of recommendations made to the customers and to keep the latency of recommendations within a stringent limit. Such requirements make architecting a recommender system a challenge. This challenge is exacerbated when different ML/DL models are employed simultaneously. This paper presents how we accelerated a recommender system that contained a state-of-the-art Graph neural network (GNN) based DL model and a dot product-based ML model. The ML model was used offline, where its recommendations were cached, and the GNN-based model provided recommendations in real time. The merging of offline results with the results provided by the real-time session-based recommendation model again posed a challenge for latency. We could reduce the model's recommendation latency from 1.5 seconds to under 65 milliseconds with careful re-architecting. We also improved the throughput from 1 recommendation per second to 1500 recommendations per second on a VM with 16-core CPU and 64 GB RAM.
References
[1]
R. Sharma and R. Singh, "Evolution of recommender systems from ancient times to modern era: A survey," Indian Journal of Science and Technology, vol. 9, 05 2016.
[2]
R. Singhal, G. Shroff, M. Kumar, S. R. Choudhury, S. Kadarkar, R. Virk, S. Verma, and V. Tewari, "Fast online 'next best offers' using deep learning," in Proceedings of the ACM India Joint International Conference on Data Science and Management of Data, ser. CoDS-COMAD '19. New York, NY, USA: Association for Computing Machinery, 2019, p. 217--223. [Online].
[3]
E. D. Berger, "Scalene: Scripting-language aware profiling for python," 2020.
[4]
C. Zisopoulos, S. Karagiannidis, G. Demirtsoglou, and S. Antaris, "Content-based recommendation systems," 11 2008.
[5]
B. Schafer, B. J, D. Frankowski, Dan, Herlocker, Jon, Shilad, and S. Sen, "Collaborative filtering recommender systems," 01 2007.
[6]
X. Li and T. Murata, "A knowledge-based recommendation model utilizing formal concept analysis and association," in 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE), vol. 4, 2010, pp. 221--226.
[7]
F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, "The graph neural network model," IEEE Transactions on Neural Networks, vol. 20, no. 1, pp. 61--80, 2009.
[8]
W. Jiang, Z. He, S. Zhang, K. Zeng, L. Feng, J. Zhang, T. Liu, Y. Li, J. Zhou, C. Zhang, and G. Alonso, FleetRec: Large-Scale Recommendation Inference on Hybrid GPU-FPGA Clusters. New York, NY, USA: Association for Computing Machinery, 2021, p. 3097--3105. [Online].
[9]
W. Jiang, Z. He, S. Zhang, T. B. Preußer, K. Zeng, L. Feng, J. Zhang, T. Liu, Y. Li, J. Zhou, C. Zhang, and G. Alonso, "Microrec: Efficient recommendation inference by hardware and data structure solutions," 2021.
[10]
A. Krishnan, M. Nambiar, N. Sumeet, and S. Iqbal, "Performance model and profile guided design of a high-performance session based recommendation engine," in Proceedings of the 2022 ACM/SPEC on International Conference on Performance Engineering, ser. ICPE '22. New York, NY, USA: Association for Computing Machinery, 2022, p. 133--144. [Online].
[11]
P. Gupta, D. Garg, P. Malhotra, L. Vig, and G. Shroff, "Niser: Normalized item and session representations with graph neural networks," 09 2019.
[12]
V. Zanoyan, "Zipline," www.databricks.com.
[13]
T. Sell and W. Pienaar, "Feast feature store," URL https://cloud.google.com/blog/products/ai-machine-learning/introducing-feast-an-open-source-feature-store-for-machine-learning. [Online]. Available: https://cloud.google.com/blog/products/ai-machine-learning/introducing-feast-an-open-source-feature-store-for-machine-learning
[14]
J. Downing, "Hopsworks feature store," www.logicalclocks.com.
Index Terms
- Scalable High-Performance Architecture for Evolving Recommender System
Recommendations
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data MiningRecommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques
A new method is developed for recommender systems.The recommender system is developed based on collaborative filtering.Scalability and sparsity issues in recommender systems are solved.MovieLens and Yahoo! Webscope R4 datasets are used for method ...
Acquiring User Information Needs for Recommender Systems
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03Most recommender systems attempt to use collaborative filtering, content-based filtering or hybrid approach to recommend items to new users. Collaborative filtering recommends items to new users based on their similar neighbours, and content-based ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 May 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
EuroMLSys '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 18 of 26 submissions, 69%
Upcoming Conference
EuroSys '25
- Sponsor:
- sigops
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 71Total Downloads
- Downloads (Last 12 months)37
- Downloads (Last 6 weeks)3
Reflects downloads up to 12 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in