DGTEN: A Robust Deep Gaussian based Graph Neural Network for Dynamic Trust Evaluation with Uncertainty-Quantification Support

2025-10-08

AI Summary

Addressing challenges in dynamic graph trust assessment—including difficulty modeling temporal evolution, weak uncertainty quantification, and poor robustness against adversarial attacks—this paper proposes the first unified graph neural network framework integrating uncertainty modeling, temporal dynamics analysis, and adversarial defense. Methodologically, it couples Gaussian-distribution-based message passing, hybrid absolute-Gaussian hourglass positional encoding, Kolmogorov–Arnold network (KAN)-enhanced attention, and ODE-driven residual learning. Additionally, it introduces an adaptive robust ensemble mechanism leveraging cosine and Jaccard similarities for fine-grained uncertainty quantification and risk-aware inference. Evaluated on datasets including Bitcoin-Alpha, the framework achieves a 10.77% improvement in Matthews Correlation Coefficient (MCC) for single-time-step prediction, a 16.41% gain in cold-start scenarios, and up to 11.63% higher MCC under adversarial attacks—substantially outperforming state-of-the-art baselines.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Dynamic trust evaluation in large, rapidly evolving graphs requires models that can capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-based Trust Evaluation Network) introduces a unified graph framework that achieves all three by combining uncertainty-aware message passing, expressive temporal modeling, and built-in defenses against trust-targeted attacks. It represents nodes and edges as Gaussian distributions so that both semantic signals and epistemic uncertainty propagate through the graph neural network, enabling risk-aware trust decisions rather than overconfident guesses. To model how trust evolves, it employs hybrid Absolute-Gaussian-Hourglass (HAGH) positional encoding with Kolmogorov-Arnold network-based unbiased multi-head attention, followed by an ordinary differential equation (ODE)-based residual learning module to jointly capture abrupt shifts and smooth trends. Robust adaptive ensemble coefficient analysis prunes or down-weights suspicious interactions using complementary cosine and Jaccard similarity measures, mitigating reputation laundering, sabotage, and on/off attacks. On two signed Bitcoin trust networks, DGTEN delivers significant improvements: in single-timeslot prediction on Bitcoin-Alpha, it improves MCC by 10.77% over the best dynamic baseline; in the cold-start scenario, it achieves a 16.41% MCC gain - the largest across all tasks and datasets. Under adversarial on/off attacks, it surpasses the baseline by up to 11.63% MCC. These results validate the effectiveness of the unified DGTEN framework.

Problem

• Evaluating dynamic trust in rapidly evolving graphs with uncertainty quantification
• Modeling trust evolution through temporal patterns and abrupt changes
• Defending against adversarial attacks on trust networks using robust ensembles

Innovation

• Uses Gaussian distributions for uncertainty-aware graph propagation
• Employs hybrid encoding with ODE-based residual learning
• Applies adaptive ensemble analysis to mitigate adversarial attacks