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

Understanding attention in graph neural networks

2019-05-08
Boris Knyazev, Graham W. Taylor, Mohamed R. Amer

Abstract

We aim to better understand attention over nodes in graph neural networks and identify factors influencing its effectiveness. Motivated by insights from the work on Graph Isomorphism Networks (Xu et al., 2019), we design simple graph reasoning tasks that allow us to study attention in a controlled environment. We find that under typical conditions the effect of attention is negligible or even harmful, but under certain conditions it provides an exceptional gain in performance of more than 40% in some of our classification tasks. However, we have yet to satisfy these conditions in practice.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.02850

PDF

http://arxiv.org/pdf/1905.02850


Similar Posts

Comments