TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction

2026-06-15

AI Summary

Existing trust prediction methods treat heterogeneous trust evidence uniformly, overlooking their distinct roles in dynamic trust modeling and thereby yielding inaccurate predictions. This work proposes the TCHG framework, which, for the first time, decouples trust evidence into three functional channels—entity reliability, interaction behavior reliability, and contextual trust—to respectively govern message admission, propagation intensity, and propagation patterns in graph neural networks. TCHG further incorporates independent temporal states with non-uniform decay to capture multi-scale dynamic evolution and integrates a context-aware operator selection mechanism with probabilistic calibration. Experimental results demonstrate that TCHG significantly outperforms state-of-the-art methods across multiple public datasets, achieving more accurate and high-confidence dynamic trust predictions.

Abstract

Trust prediction infers latent user-user trust relations and provides important support for social recommendation, fake-review and manipulation detection, and risk identification. Graph neural networks have become a prominent approach to trust prediction because of their ability to learn network structures and complex trust dependencies. However, existing methods often rely on a unified representation of trust signals and do not disentangle heterogeneous trust evidence into separate evidence channels, failing to exploit the distinct roles that different evidence channels should play during trust modeling. To address this gap, this paper argues that trust evidence should not be treated as an undifferentiated input, but should be decomposed and used as functional control factors over graph propagation. We propose TCHG, a tri-trust conditioned heterogeneous graph learning framework that decomposes trust evidence into three channels and assigns them distinct functional roles in propagation: entity reliability governs message admission, interaction-behavior reliability modulates propagation strength, and contextual trust adjusts the propagation mode through context-conditioned operator selection. Since the three evidence channels evolve at different temporal scales, TCHG maintains independent temporal states with non-uniform decay rates to prevent rapidly changing contextual signals from overwriting slowly accumulated entity reliability. It further predicts trust probability and calibrates the output probability, improving predictive confidence under sparse or conflicting evidence. Extensive experiments on multiple public trust datasets show that TCHG achieves effective and reliable trust prediction compared with representative trust prediction and heterogeneous graph baselines.

Problem

• trust prediction
• heterogeneous graph
• trust evidence
• graph neural networks
• dynamic trust

Innovation

• heterogeneous graph learning
• trust prediction
• evidence disentanglement
• temporal state modeling
• graph neural networks