papers AI Learner
The Github is limit! Click to go to the new site.

Are Graph Neural Networks Miscalibrated?

2019-05-07
Leonardo Teixeira, Brian Jalaian, Bruno Ribeiro

Abstract

Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For this purpose, obtaining calibrated models is essential. In this work, we analyze the calibration of state-of-the-art GNNs on multiple datasets. Our experiments show that GNNs can be calibrated in some datasets but also badly miscalibrated in others, and that state-of-the-art calibration methods are helpful but do not fix the problem.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.02296

PDF

https://arxiv.org/pdf/1905.02296


Similar Posts

Comments