Paper ID: 2206.10691
Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
Gleb Bazhenov, Sergei Ivanov, Maxim Panov, Alexey Zaytsev, Evgeny Burnaev
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.
Submitted: Jun 21, 2022