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.
翻译:使用中央数据库培训建议模式需要常规推荐系统,然而,由于数据隐私问题,当多个缔约方参与推荐系统培训时,这往往不切实际。联邦学习似乎是数据孤立和隐私问题的极好解决办法。最近,图表神经网络(GNN)正在成为联邦推荐系统的一个很有希望的方法。然而,一个关键的挑战是如何在维护图形结构隐私的同时进行嵌入传播。对以GNN为基础的联合推荐系统开展的研究很少。我们的研究提出了第一个以GNN为基础的垂直联合推荐系统,称为VerFedGNN。我们设计了一个框架,以传输:(一) 使用随机投影对邻居嵌入的汇总,以及(二) 由四分位化机制渗透的公共参数梯度。经验性研究表明,VerFedGNNN与现有的隐私保护GNN框架相比具有竞争性预测准确性,同时加强用户互动信息的隐私保护。</s>