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

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 cloudbased 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.

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

“…4) Same features, different labels: The conditional distribution of labels given features may differ between edges. For example, the symbol EdgeRec System [28] Auto-Split [218] CoEdge [219] Colla [220] DCCL [30] MC 2 -SF [221] FedAvg [27] FML [222] Personalized FedAvg [223] HyperCluster [224] Federated Evaluation [225] represents correct in many countries and incorrect in some others (e.g., Japan); and 5) Quantity skew: Clients can store drastically varying volumes of data.…”

“…One more intensive type of edge-cloud collaboration could be bidirectional, where we consider the independent modeling on each side and they maintain the interactive feedback to each other during both the training and serving. One recent exploration is a Slow-Fast Learning mechanism for Edge-Cloud Collaborative recommendation developed on Alibaba Gemini Platform [221]. In MC 2 -SF, the slow component (the cloud model) helps the fast component (the edge model) make predictions by delivering the auxiliary latent representations; and conversely, the fast component transfers the feedbacks from the real-time exposed items to the slow component, which helps better capture the user interests.…”

“…That is to say, we cannot completely understand the characteristics of data on the edge side by only training the model on the current cloud-based datasets. On the other hand, for the interactive scenarios like Gemini [221], it requires the specific data collection to guarantee the distribution consistency between the training and the test. Simply simulation on the cloud-based dataset by decomposition cannot recover the real-world scenarios.…”