Credal Graph Neural Networks

TL;DR

This paper introduces credal graph neural networks (CGNNs) that output set-valued predictions for improved uncertainty quantification in GNNs, especially under distributional shifts and heterophilic graph conditions.

Contribution

It is the first to extend credal learning to GNNs, developing a novel approach that leverages layer-wise information propagation for uncertainty estimation.

Findings

CGNNs provide more reliable epistemic uncertainty estimates.

They outperform existing methods under out-of-distribution conditions.

State-of-the-art results on heterophilic graphs.

Abstract

Uncertainty quantification is essential for deploying reliable Graph Neural Networks (GNNs), where existing approaches primarily rely on Bayesian inference or ensembles. In this paper, we introduce the first credal graph neural networks (CGNNs), which extend credal learning to the graph domain by training GNNs to output set-valued predictions in the form of credal sets. To account for the distinctive nature of message passing in GNNs, we develop a complementary approach to credal learning that leverages different aspects of layer-wise information propagation. We assess our approach on uncertainty quantification in node classification under out-of-distribution conditions. Our analysis highlights the critical role of the graph homophily assumption in shaping the effectiveness of uncertainty estimates. Extensive experiments demonstrate that CGNNs deliver more reliable representations of epistemic uncertainty and achieve state-of-the-art performance under distributional shift on heterophilic graphs.