Understanding Attention and Generalization in Graph Neural Networks

We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy graphs... (read more)

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification COLLAB Weak-supervised ChebyNet Accuracy 66.97% # 25
Graph Classification D&D Weak-supervised ChebyNet Accuracy 78.36% # 20
Graph Classification PROTEINS Weak-supervised ChebyNet Accuracy 77.09% # 18

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet