A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs
MCML Authors
Yuesong Shen
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
Abstract
Yuesong Shen
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
Abstract
Current graph neural networks (GNNs) that tackle node classification on graphs tend to only focus on nodewise scores and are solely evaluated by nodewise metrics. This limits uncertainty estimation on graphs since nodewise marginals do not fully characterize the joint distribution given the graph structure. In this work, we propose novel edgewise metrics, namely the edgewise expected calibration error (ECE) and the agree/disagree ECEs, which provide criteria for uncertainty estimation on graphs beyond the nodewise setting. Our experiments demonstrate that the proposed edgewise metrics can complement the nodewise results and yield additional insights. Moreover, we show that GNN models which consider the structured prediction problem on graphs tend to have better uncertainty estimations, which illustrates the benefit of going beyond the nodewise setting.
inproceedings
New Frontiers in Graph Learning @NeurIPS 2022
Workshop on New Frontiers in Graph Learning at the 36th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Nov 28-Dec 09, 2022.Authors
H. H.-H. Hsu • Y. Shen • D. CremersLinks
URLResearch Area
BibTeXKey: HSC22