Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective. (arXiv:2206.10691v1 [cs.LG])

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.

arxiv classification detection graph lg perspective uncertainty