With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks. Compared to the straightforward mobile-based modeling appended to the cloud-based modeling, we propose a Slow-Fast learning mechanism to make the Mobile-Cloud Collaborative recommendation (MC2-SF) mutual benefit. Specially, in our MC2-SF, the cloud-based model and the mobile-based model are respectively treated as the slow component and the fast component, according to their interaction frequency in real-world scenarios. During training and serving, they will communicate the prior/privileged knowledge to each other to help better capture the user interests about the candidates, resembling the role of System I and System II in the human cognition. We conduct the extensive experiments on three benchmark datasets and demonstrate the proposed MC2-SF outperforms several state-of-the-art methods.
@article{arxiv.2109.12314,
title = {MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation},
author = {Zeyuan Chen and Jiangchao Yao and Feng Wang and Kunyang Jia and Bo Han and Wei Zhang and Hongxia Yang},
journal= {arXiv preprint arXiv:2109.12314},
year = {2021}
}