Uncertainty Quantification on Graph Learning: A Survey

TL;DR

This survey reviews recent developments in uncertainty quantification techniques specifically applied to graphical models, including graph neural networks and foundation models, highlighting key challenges and future directions.

Contribution

It uniquely focuses on UQ for graphical models, organizing literature by uncertainty representation and handling, and synthesizing emerging trends and challenges.

Findings

Systematic examination of UQ methods for graphical models.

Identification of key challenges and opportunities in the field.

Bridging gaps between uncertainty quantification and graphical models.

Abstract

Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustworthiness are often limited by the inherent randomness in data generation and the lack of knowledge to accurately model real-world complexities. There has been increased interest in developing uncertainty quantification (UQ) techniques tailored to graphical models. In this survey, we systematically examine existing works on UQ for graphical models. This survey distinguishes itself from most existing UQ surveys by specifically concentrating on graphical models, including graph neural networks and graph foundation models. We organize the literature along two complementary dimensions: uncertainty representation and uncertainty handling. By synthesizing both established methodologies and emerging trends, we aim to bridge gaps in understanding key challenges and opportunities in UQ for graphical models, inspiring researchers on graphical models or uncertainty quantification to make further advancements at the cross of the two fields.