Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach

TL;DR

This paper introduces EFGNN, a novel graph neural network that incorporates evidence theory and a fusion mechanism to quantify and improve prediction trustworthiness and accuracy in node classification tasks.

Contribution

The paper proposes a new GNN architecture that explicitly models uncertainty using evidence theory and a fusion mechanism, enhancing reliability and robustness.

Findings

EFGNN improves node classification accuracy.

The model effectively quantifies prediction uncertainty.

EFGNN demonstrates robustness against potential attacks.

Abstract

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.