Hierarchical Uncertainty-Aware Graph Neural Network

2025-04-28

AI Summary

To address the insufficient robustness and interpretability of Graph Neural Networks (GNNs) under data sparsity, noise corruption, and adversarial perturbations, this paper proposes the first end-to-end unified framework that jointly integrates multi-scale hierarchical clustering, layer-wise Bayesian uncertainty estimation, and structure-preserving self-supervised embedding diversity learning. Its key contributions are: (1) the first joint optimization of graph hierarchical structure learning and principled uncertainty modeling, yielding probabilistic predictions, well-calibrated uncertainty estimates, and formally derived robustness bounds; and (2) an adaptive attention-based message passing mechanism coupled with contrastive graph embedding, balancing structural fidelity and representation diversity. Evaluated on standard benchmarks, the method achieves state-of-the-art robustness and interpretability for both node-level and graph-level tasks, significantly improving resilience against noise and adversarial attacks.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent research on graph neural networks (GNNs) has explored mechanisms for capturing local uncertainty and exploiting graph hierarchies to mitigate data sparsity and leverage structural properties. However, the synergistic integration of these two approaches remains underexplored. In this work, we introduce a novel architecture, the Hierarchical Uncertainty-Aware Graph Neural Network (HU-GNN), which unifies multi-scale representation learning, principled uncertainty estimation, and self-supervised embedding diversity within a single end-to-end framework. Specifically, HU-GNN adaptively forms node clusters and estimates uncertainty at multiple structural scales from individual nodes to higher levels. These uncertainty estimates guide a robust message-passing mechanism and attention weighting, effectively mitigating noise and adversarial perturbations while preserving predictive accuracy on both node- and graph-level tasks. We also offer key theoretical contributions, including a probabilistic formulation, rigorous uncertainty-calibration guarantees, and formal robustness bounds. Finally, by incorporating recent advances in graph contrastive learning, HU-GNN maintains diverse, structurally faithful embeddings. Extensive experiments on standard benchmarks demonstrate that our model achieves state-of-the-art robustness and interpretability.

Problem

• Integrates multi-scale learning with uncertainty estimation in GNNs
• Mitigates noise and adversarial perturbations while preserving accuracy
• Ensures diverse and structurally faithful graph embeddings

Innovation

• Unifies multi-scale representation and uncertainty estimation
• Adaptive node clustering with uncertainty-guided message-passing
• Incorporates graph contrastive learning for diverse embeddings