Research Area: Machine Learning
Recommendation models have been widely embedded in various online services, while most of which are designed with the assumption that users original behaviors are available in a central server. This may cause the privacy issue. As a response, we follow a recent work called federated collaborative filtering (FCF) for item recommendation with implicit feedback and propose a novel and generic federated recommendation (FedRec) framework for rating prediction with explicit feedback. Specifically, we federate some basic and advanced factorization-based recommendation models both in batch style and in stochastic style. More importantly, in order to protect the private information of which items each user has rated, as well as not to significantly increase the computational and communication cost, we design two simple but effective strategies, i.e., user averaging and hybrid filling, in which some (instead of all) unrated items are randomly sampled and assigned with some virtual ratings accordingly. Empirical studies on two public datasets show the effectiveness of our FedRec in terms of the closeness of a federated model and an unfederated one, and the usefulness of the two filling strategies.
Keywords:
Author(s) Name: Guanyu Lin; Feng Liang; Weike Pan; Zhong Ming
Journal name: IEEE Intelligent Systems
Conferrence name:
Publisher name: IEEE
DOI: 10.1109/MIS.2020.3017205
Volume Information: Volume: 36 Issue: 5, Page(s): 21 - 30
