Abstract
In recent years, word embedding models receive tremendous research attentions due to their capability of capturing textual semantics. This study investigates the issue of employing word embedding models into storage-constrained edge devices for personalized item-of-interest recommendation in a smart store. The challenge lies in that the existing embedding models are often too large to fit into a storage-constrained edge device. One naive idea is to reside the word embedding model in a secondary storage and process recommendation with that storage. However, this idea suffers from the burden of additional traffics. To this end, we propose a framework called Word Embedding Quantization (WEQ) which constructs an index upon a given word embedding model and stores the index in the primary storage to enable the use of the word embedding model by edge devices. One challenge for using the index is that the exact user profile is no longer ensured. However, we find that there are opportunities for computing the correct recommendation results by knowing only an inexact user profile. In this paper, we propose a series of techniques that leverage the opportunities for computing candidates with the goal of minimizing the accessing cost to a secondary storage in edge devices. Experiments are performed to verify the efficiency of the proposed techniques, demonstrating the feasibility of the proposed framework.
Similar content being viewed by others
References
Penev A, Wong RK (2009) Framework for timely and accurate ads on mobile devices. In: Proceedings of the 18th ACM conference on Information and knowledge management. ACM, pp 1067– 1076
Zheng Y, Xie X, MA W-Y (2010) Geolife: A collaborative social networking service among user, location and trajectory. IEEE Data Eng Bull 33.2:32–39
Fan Y-C et al (2016) A framework for enabling user preference profiling through Wi-Fi logs. IEEE Trans Knowl Data Eng 28.3:592–603
Bilenko M, Richardson M (2011) Predictive client-side profiles for personalized advertising. In: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 413–421
Zhuang J, et al. (2011) When recommendation meets mobile: contextual and personalized recommendation on the go. In: Proceedings of the 13th international conference on Ubiquitous computing. ACM, pp 153–162
Sarwar B et al (2001) Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th international conference on World Wide Web. ACM, pp 285–295
Zhu H et al (2015) Mining mobile user preferences for personalized context-aware recommendation. ACM Trans Intell Syst Technol (TIST) 4(58):5
Yang X et al (2012) On top-k recommendation using social networks. In: Proceedings of the sixth ACM conference on Recommender systems. ACM, pp 67–74
Mikolov T et al (2013) Efficient estimation of word representations in vector space. arXiv:1301.3781
Mikolov Tx et al (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119
Buciluă C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 535–541
Jaderberg M, Vedaldi A, Zisserman A (2014) Speeding up convolutional neural networks with low rank expansions. arXiv:1405.3866
Zhang J, Mouratidis K, Pang H (2014) Global immutable region computation. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. ACM, pp 1151–1162
Li Y et al (2016) Context-aware advertisement recommendation for high-speed social news feeding. In: 2016 IEEE 32nd international conference on Data engineering (ICDE). IEEE, pp 505–516
Huang W et al (2012) Efficient safe-region construction for moving top-k spatial keyword queries. In: Proceedings of the 21st ACM international conference on Information and knowledge management. ACM, pp 932–941
Acknowledgments
This research was supported by the Ministry of Science and Technology Taiwan R.O.C. under grant number 106-2221-E-005-082-, and also partially supported by Industrial Technology Research Institute, Taiwan.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fan, YC., Huang, SY., Chen, YY. et al. Word Embedding Quantization for Personalized Recommendation on Storage-Constrained Edge Devices in a Smart Store. Mobile Netw Appl 27, 70–83 (2022). https://doi.org/10.1007/s11036-020-01710-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11036-020-01710-4