Title | ||
---|---|---|
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology |
Abstract | ||
---|---|---|
To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a key property of graph topology encoding path of various lengths. We find that GCNs are rather restrictive in learning graph moments. Without careful design, GCNs can fail miserably even with multiple layers and nonlinear activation functions. We analyze theoretically the expressiveness of GCNs, concluding that a modular GCN design, using different propagation rules with residual connections could significantly improve the performance of GCN. We demonstrate that such modular designs are capable of distinguishing graphs from different graph generation models for surprisingly small graphs, a notoriously difficult problem in network science. Our investigation suggests that, depth is much more influential than width, with deeper GCNs being more capable of learning higher order graph moments. Additionally, combining GCN modules with different propagation rules is critical to the representation power of GCNs. |
Year | Venue | Keywords |
---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | modular design,network science |
Field | DocType | Volume |
Computer science,Graph neural networks,Theoretical computer science,Artificial intelligence,Topological graph theory,Machine learning | Conference | 32 |
ISSN | Citations | PageRank |
1049-5258 | 3 | 0.37 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nima Dehmamy | 1 | 4 | 2.07 |
Albert-lászló Barabási | 2 | 4649 | 1107.35 |
Qi Yu | 3 | 188 | 12.87 |