TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature

TL;DR

TrustGNN introduces a novel graph neural network framework that effectively models the propagative and composable properties of trust graphs, leading to improved trust evaluation accuracy in real-world applications.

Contribution

The paper proposes TrustGNN, a GNN-based trust evaluation method that incorporates the propagative and composable nature of trust graphs, which was not adequately addressed in prior work.

Findings

TrustGNN significantly outperforms existing methods on real-world datasets.

The model effectively captures the propagative processes of trust.

Analytical experiments validate the importance of key design components.

Abstract

Trust evaluation is critical for many applications such as cyber security, social communication and recommender systems. Users and trust relationships among them can be seen as a graph. Graph neural networks (GNNs) show their powerful ability for analyzing graph-structural data. Very recently, existing work attempted to introduce the attributes and asymmetry of edges into GNNs for trust evaluation, while failed to capture some essential properties (e.g., the propagative and composable nature) of trust graphs. In this work, we propose a new GNN based trust evaluation method named TrustGNN, which integrates smartly the propagative and composable nature of trust graphs into a GNN framework for better trust evaluation. Specifically, TrustGNN designs specific propagative patterns for different propagative processes of trust, and distinguishes the contribution of different propagative processes to create new trust. Thus, TrustGNN can learn comprehensive node embeddings and predict trust relationships based on these embeddings. Experiments on some widely-used real-world datasets indicate that TrustGNN significantly outperforms the state-of-the-art methods. We further perform analytical experiments to demonstrate the effectiveness of the key designs in TrustGNN.