Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective

Understand

The problem of out-of-distribution detection for graph classification is far from being solved.

• The existing models tend to be overconfident about OOD examples or completely ignore the detection task.
• In this work, we consider this problem from the uncertainty estimation perspective and perform the comparison of several recently proposed methods.
• In our experiment, we find that there is no universal approach for OOD detection, and it is important to consider both graph representations and predictive categorical distribution.