基于联邦学习的上下文感知深度学习QoS预测方法

he rapid development of cloud computing technology has made cloud service recommendations a current research hotspot. QoS reflects the non-functional attributes of services, and cloud service recommendations based on QoS prediction can best meet user needs. Traditional collaborative filtering and matrix factorizationmethods are prone to data sparsity and cold start problems. In this paper, we propose a context-aware deep learning QoS prediction method based on federated learning. Combining the contextual features of users and services for neural network learning, and combining with federated learning techniques, the model is learned at each client, and then the model parameters are aggregated and updated at a central server process, fully protecting the data privacy of users. We conduct experiments on a real-world dataset and compare them with several classical algorithms, and the experimental results validate the effectiveness of the QoS prediction algorithm proposed in this paper.