GNN4FR: A Lossless GNN-based Federated Recommendation Framework
This addresses privacy concerns in recommender systems for users under regulations like GDPR, though it appears incremental as it adapts existing federated learning to GNNs.
The paper tackles the problem of preserving user privacy in graph neural network-based recommender systems by introducing a lossless federated recommendation framework that enables full-graph training without leaking private interaction data, achieving training equivalence to non-federated methods.
Graph neural networks (GNNs) have gained wide popularity in recommender systems due to their capability to capture higher-order structure information among the nodes of users and items. However, these methods need to collect personal interaction data between a user and the corresponding items and then model them in a central server, which would break the privacy laws such as GDPR. So far, no existing work can construct a global graph without leaking each user's private interaction data (i.e., his or her subgraph). In this paper, we are the first to design a novel lossless federated recommendation framework based on GNN, which achieves full-graph training with complete high-order structure information, enabling the training process to be equivalent to the corresponding un-federated counterpart. In addition, we use LightGCN to instantiate an example of our framework and show its equivalence.