Device-Cloud Collaborative Recommendation via Meta Controller
Jiangchao Yao, Feng Wang, Xichen Ding, Shaohu Chen, Bo Han, Jingren, Zhou, Hongxia Yang

TL;DR
This paper introduces a meta controller that dynamically manages device-cloud collaboration in recommendation systems, addressing inflexibility and dataset issues, and demonstrating promising results in industrial scenarios.
Contribution
It proposes a novel meta controller framework for flexible device-cloud recommendation collaboration and introduces an efficient causal sample construction method.
Findings
Meta controller improves recommendation adaptability.
Counterfactual sample construction enhances training.
Experimental results show effectiveness in industrial scenarios.
Abstract
On-device machine learning enables the lightweight deployment of recommendation models in local clients, which reduces the burden of the cloud-based recommenders and simultaneously incorporates more real-time user features. Nevertheless, the cloud-based recommendation in the industry is still very important considering its powerful model capacity and the efficient candidate generation from the billion-scale item pool. Previous attempts to integrate the merits of both paradigms mainly resort to a sequential mechanism, which builds the on-device recommender on top of the cloud-based recommendation. However, such a design is inflexible when user interests dramatically change: the on-device model is stuck by the limited item cache while the cloud-based recommendation based on the large item pool do not respond without the new re-fresh feedback. To overcome this issue, we propose a meta…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · IoT and Edge/Fog Computing · Machine Learning and ELM
