Web: http://arxiv.org/abs/2206.10691

June 23, 2022, 1:10 a.m. | Gleb Bazhenov, Sergei Ivanov, Maxim Panov, Alexey Zaytsev, Evgeny Burnaev

cs.LG updates on arXiv.org arxiv.org

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

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY