@article{Yuan2024, 
author = {Rui Yuan and Shunmei Meng and Ruihan Dou and Xinna Wang},
title = {Modeling Long- and Short-Term Service Recommendations with a Deep Multi-Interest Network for Edge Computing},
year = {2024},
journal = {Tsinghua Science and Technology},
volume = {29},
number = {1},
pages = {86-98},
keywords = {recommender system, logarithmic network, nonlocal network},
url = {https://www.sciopen.com/article/10.26599/TST.2022.9010054},
doi = {10.26599/TST.2022.9010054},
abstract = {Edge computing platforms enable application developers and content providers to provide context-aware services (such as service recommendations) using real-time wireless access network information. How to recommend the most suitable candidate from these numerous available services is an urgent task. Click-through rate (CTR) prediction is a core task of traditional service recommendation. However, many existing service recommender systems do not exploit user mobility for prediction, particularly in an edge computing environment. In this paper, we propose a model named long and short-term user preferences modeling with a multi-interest network based on user behavior. It uses a logarithmic network to capture multiple interests in different fields, enriching the representations of user short-term preferences. In terms of long-term preferences, users’ comprehensive preferences are extracted in different periods and are fused using a nonlocal network. Extensive experiments on three datasets demonstrate that our model relying on user mobility can substantially improve the accuracy of service recommendation in edge computing compared with the state-of-the-art models.}
}