Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
graph_embedding [2018/10/05 10:40]
admin
graph_embedding [2018/10/05 10:42] (current)
admin
Line 318: Line 318:
 https://​arxiv.org/​abs/​1810.00826v1 How Powerful are Graph Neural Networks? https://​arxiv.org/​abs/​1810.00826v1 How Powerful are Graph Neural Networks?
  
-Our results characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures. We then develop a simple architecture that is provably the most expressive among the class of GNNs and is as powerful as the Weisfeiler-Lehman graph isomorphism test. +Our results characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures. We then develop a simple architecture that is provably the most expressive among the class of GNNs and is as powerful as the Weisfeiler-Lehman graph isomorphism test. An interesting direction for future work is to go beyond the neighborhood aggregation (or messageĀ 
 +passing) framework in order to pursue even more powerful architectures for learning with graphs.