Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation

TL;DR

This paper introduces a user-governed federated recommendation system that allows users to control their data sharing, utilizing a graph neural network model with collaborative training and graph mending to improve recommendation quality.

Contribution

It proposes a novel federated recommendation architecture enabling user-controlled data sharing and introduces CDCGNNFed, a graph neural network model with collaborative training and graph mending strategies.

Findings

Effective in leveraging user-controlled data sharing

Improves recommendation accuracy with graph neural networks

Demonstrates superior performance on public datasets

Abstract

Federated recommender systems (FedRecs) have gained significant attention for their potential to protect user's privacy by keeping user privacy data locally and only communicating model parameters/gradients to the server. Nevertheless, the currently existing architecture of FedRecs assumes that all users have the same 0-privacy budget, i.e., they do not upload any data to the server, thus overlooking those users who are less concerned about privacy and are willing to upload data to get a better recommendation service. To bridge this gap, this paper explores a user-governed data contribution federated recommendation architecture where users are free to take control of whether they share data and the proportion of data they share to the server. To this end, this paper presents a cloud-device collaborative graph neural network federated recommendation model, named CDCGNNFed. It trains user-centric ego graphs locally, and high-order graphs based on user-shared data in the server in a collaborative manner via contrastive learning. Furthermore, a graph mending strategy is utilized to predict missing links in the graph on the server, thus leveraging the capabilities of graph neural networks over high-order graphs. Extensive experiments were conducted on two public datasets, and the results demonstrate the effectiveness of the proposed method.