Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
This addresses the need for trustworthy predictions in graph-based applications, though it appears incremental as it builds on existing GNN and evidence theory methods.
The paper tackles the problem of unreliable predictions in graph neural networks (GNNs) due to unaccounted uncertainty in class probabilities, proposing an Evidence Fusing Graph Neural Network (EFGNN) that improves node classification accuracy and quantifies prediction uncertainty, with experimental results showing effectiveness in accuracy and trustworthiness.
Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of class probabilities that vary with the depth of the model, leading to unreliable and risky predictions in real-world scenarios. To bridge the gap, in this paper, we propose a novel Evidence Fusing Graph Neural Network (EFGNN for short) to achieve trustworthy prediction, enhance node classification accuracy, and make explicit the risk of wrong predictions. In particular, we integrate the evidence theory with multi-hop propagation-based GNN architecture to quantify the prediction uncertainty of each node with the consideration of multiple receptive fields. Moreover, a parameter-free cumulative belief fusion (CBF) mechanism is developed to leverage the changes in prediction uncertainty and fuse the evidence to improve the trustworthiness of the final prediction. To effectively optimize the EFGNN model, we carefully design a joint learning objective composed of evidence cross-entropy, dissonance coefficient, and false confident penalty. The experimental results on various datasets and theoretical analyses demonstrate the effectiveness of the proposed model in terms of accuracy and trustworthiness, as well as its robustness to potential attacks. The source code of EFGNN is available at https://github.com/Shiy-Li/EFGNN.