论文标题
从不确定性估计的角度迈向图分类中的OOD检测
Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
论文作者
论文摘要
用于图形分类的分布外检测的问题远未解决。现有的模型往往对OOD示例过分自信，或者完全忽略检测任务。在这项工作中，我们从不确定性估计的角度考虑了这个问题，并进行了几种最近提出的方法的比较。在我们的实验中，我们发现没有通用的OOD检测方法，并且重要的是考虑图表和预测分类分布。
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.
