Linear Opinion Pooling for Uncertainty Quantification on Graphs
This addresses uncertainty estimation for graph-structured data, which is important for applications like social networks or bioinformatics, but appears incremental as it builds on existing principles.
The paper tackles uncertainty quantification in semi-supervised node classification on graphs by distinguishing aleatoric and epistemic uncertainty, proposing a method using mixtures of Dirichlet distributions and linear opinion pooling, and demonstrates effectiveness across multiple datasets.
We address the problem of uncertainty quantification for graph-structured data, or, more specifically, the problem to quantify the predictive uncertainty in (semi-supervised) node classification. Key questions in this regard concern the distinction between two different types of uncertainty, aleatoric and epistemic, and how to support uncertainty quantification by leveraging the structural information provided by the graph topology. Challenging assumptions and postulates of state-of-the-art methods, we propose a novel approach that represents (epistemic) uncertainty in terms of mixtures of Dirichlet distributions and refers to the established principle of linear opinion pooling for propagating information between neighbored nodes in the graph. The effectiveness of this approach is demonstrated in a series of experiments on a variety of graph-structured datasets.