MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation

TL;DR

This paper introduces MC$^2$-SF, a collaborative recommendation framework that leverages slow cloud-based and fast mobile-based models communicating to improve user interest prediction, validated on benchmark datasets.

Contribution

Proposes a novel Slow-Fast learning mechanism for mobile-cloud collaborative recommendation, enabling mutual knowledge transfer between models of different update frequencies.

Findings

Outperforms several state-of-the-art recommendation methods

Effective in capturing user interests with real-time feedback

Validated on three benchmark datasets

Abstract

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 (MC$^2$-SF) mutual benefit. Specially, in our MC$^2$-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 MC$^2$-SF outperforms several state-of-the-art methods.