High Order Collaboration-Oriented Federated Graph Neural Network for Accurate QoS Prediction

TL;DR

This paper introduces HC-FGNN, a federated graph neural network that captures high-order user collaborations for more accurate QoS prediction while preserving user privacy.

Contribution

It proposes a novel high order collaboration mechanism in federated GNNs to better utilize implicit user interactions for QoS prediction.

Findings

HC-FGNN achieves higher prediction accuracy than existing models.

The method effectively preserves user privacy during training.

It improves computational efficiency with lightweight message aggregation.

Abstract

Predicting Quality of Service (QoS) data crucial for cloud service selection, where user privacy is a critical concern. Federated Graph Neural Networks (FGNNs) can perform QoS data prediction as well as maintaining user privacy. However, existing FGNN-based QoS predictors commonly implement on-device training on scattered explicit user-service graphs, thereby failing to utilize the implicit user-user interactions. To address this issue, this study proposes a high order collaboration-oriented federated graph neural network (HC-FGNN) to obtain accurate QoS prediction with privacy preservation. Concretely, it magnifies the explicit user-service graphs following the principle of attention mechanism to obtain the high order collaboration, which reflects the implicit user-user interactions. Moreover, it utilizes a lightweight-based message aggregation way to improve the computational efficiency. The extensive experiments on two QoS datasets from real application indicate that the proposed HC-FGNN possesses the advantages of high prediction accurate and privacy protection.