How Powerful are Graph Neural Networks?
Resource history | v1 (current) | created by janarez
Details
How Powerful are Graph Neural Networks?
see v1 | created by janarez | Add resource "The Weisfeiler-Lehman Isomorphism Test"
- Title
- How Powerful are Graph Neural Networks?
- Type
- Paper
- Created
- 2019-02-22
- Description
- Despite GNNs revolutionizing graph representation learning, there is limited understanding of their representational properties and limitations. Here, we present a theoretical framework for analyzing the expressive power of GNNs to capture different graph structures. 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.
- Link
- http://arxiv.org/abs/1810.00826
- Identifier
- no value
authors
This resource has no history of related authors.
topics
compares Graph convolutional networks (GCN)
resources
This resource has no history of related resources.