Conventional recommender systems are required to train the recommendation
model using a centralized database. However, due to data privacy concerns, this
is often impractical when multi-parties are involved in recommender system
training. Federated learning appears as an excellent solution to the data
isolation and privacy problem. Recently, Graph neural network (GNN) is becoming
a promising approach for federated recommender systems. However, a key
challenge is to conduct embedding propagation while preserving the privacy of
the graph structure. Few studies have been conducted on the federated GNN-based
recommender system. Our study proposes the first vertical federated GNN-based
recommender system, called VerFedGNN. We design a framework to transmit: (i)
the summation of neighbor embeddings using random projection, and (ii)
gradients of public parameter perturbed by ternary quantization mechanism.
Empirical studies show that VerFedGNN has competitive prediction accuracy with
existing privacy preserving GNN frameworks while enhanced privacy protection
for users’ interaction information.
Go to Source of this post
Author Of this post: <a href="http://arxiv.org/find/cs/1/au:+Mai_P/0/1/0/all/0/1">Peihua Mai</a>, <a href="http://arxiv.org/find/cs/1/au:+Pang_Y/0/1/0/all/0/1">Yan Pang</a>